m (→External links) |
Tag: rollback |
||
| (5 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
{{LangPsy}} |
{{LangPsy}} |
||
| + | {{PsyPerspective}} |
||
| + | '''Speech recognition''' (in many contexts also known as '''automatic speech recognition''', '''computer speech recognition''' or erroneously as voice recognition) is the process of converting a speech signal to a sequence of words in the form of digital data, by means of an algorithm implemented as a computer program. |
||
| + | Speech recognition applications that have emerged over the last few is years include voice dialing (''e.g.'', "Call home"), call routing (''e.g.'', "I would like to make a collect call"), domotic appliance control and content-based spoken audio search (''e.g.'' find a podcast where particular words were spoken), simple data entry (''e.g.'', entering a credit card number), preparation of structured documents (e.g., a radiology report), speech-to-text processing (text for OpenDocument, word processors, emails...); in the [[cockpit]] of some military fast jets (where it is generally referred to as [[Direct Voice Input]] - DVI -). |
||
| − | '''Speech recognition''' (in many contexts, also known as [[automatic speech recognition]], [[computer speech recognition]] or [[voice recognition]]) technologies generally represent a set of technology that allows [[computer]]s equipped with a source of sound input, such as a [[microphone]], to transform [[human speech]] to a sequence of words. Applications of speech recognition include [[transcription]] and as an alternative method of interacting with a [[computer]]. This is not to be confused with [[voice authentication]] (or [[speaker authentication]]), which recognizes only voice patterns as in security identification, or [[speaker identification]] which aims at identifying one speaker out of many. |
||
| + | Voice recognition, or better, [[automated speaker recognition|speaker recognition]] is a related process that attempts to identify the person speaking, as opposed to what is being said. |
||
| − | In a strict technical sense, the use of the term '''speech recognition''' should be differentiated from general speech applications such as a '''dictation''' (e.g. Dragon Naturally Speaking), '''voice activated telephony system''' (e.g. software provided by companies such as Nuance). '''Speech recognition''', in a strict technical sense, usually means the automatic process of transforming the sound input to a sequence of words, but applications can provide extra functionality on top of the process, like the extraction of meanings from the word sequence (e.g [[robust parser]]) or even correcting the grammar of the recognized text. |
||
| + | ==History== |
||
| − | ==Classification of Speech Recognition Systems== |
||
| + | One of the most notable domains for the commercial application of speech recognition in the United States has been health care and in particular the work of the medical transcriptionist (MT). According to industry experts, at its inception, speech recognition (SR) was sold as a way to completely eliminate transcription rather than make the transcription process more efficient, hence it was not accepted. It was also the case that SR at that time was often technically deficient. Additionally, to be used effectively, it changes to the ways physicians worked and documented clinical encounters, which many if not all were reluctant to do. The biggest limitation to speech recognition automating transcription, however, is seen as the software. The nature of narrative dictation is highly interpretive and often requires judgment that may be provided by a real human but not by an automated system. Another limitation has been the extensive amount of time required by the user and/or system provider to train the software. |
||
| + | A useful distinction in ASR is often made between "artificial syntax systems" which are usually domain specific and "natural language processing" which are usually language specific. Each of these types of application present their own particular goals and challenges. |
||
| − | Systems of speech recognition be classified by either underlying technology used or the working mode the system. |
||
| + | ==Current== |
||
| − | In terms of technology, most of the technical text books nowadays emphasize the use of [[Hidden Markov Model]] as the underlying technology. Though it should be noted that the use of [[dynamic algorithm approach]], [[neural network-based approach]] and [[knowledge-based approach]] have been studied intensively in 80s and 90s. |
||
| + | ===Health Care=== |
||
| − | In terms of working mode, from a user perspective, such systems can be classified according to the following criterions |
||
| + | In the [[health care]] domain, even in the wake of improving speech recognition technologies, medical transcriptionists (MTs) have not yet become obsolete. Many experts in the field anticipate that with increased use of speech recognition technology, the services provided may be redistributed rather than replaced. Speech recognition has not yet made the skills of MTs obsolete. |
||
| + | Speech recognition can be implemented in front-end or back-end of the medical documentation process. |
||
| − | *Whether the system is trained for one user only ('''speaker dependent''') or could be used for different speakers ('''speaker independent''') |
||
| − | *Whether they require the user to "train" the system to recognize their own particular speech patterns or not. Some refers this as '''speaker adaptation''' |
||
| − | *Whether the system requires users to break up their speech into discrete words ('''isolated word recognition''') or can recognize natural human speech which has the properties which words "stick together" (or '''coarticulated''' together). The latter case is usually called '''continuous speech''' (''' continuous speech recognition'''). Some also used the terms '''connected word recognition''' despite it is slightly less well-defined. |
||
| − | *Whether the system requires the user to push a button to start speech recognition or the system could automatically detect the beginning and the end of the utterance. |
||
| − | *Whether the system is intended for clear speech material or is designed to operate on distorted transfer channels (e.g., [[cellular telephone]]s) and possibly background noise or another speaker talking simultaneously. |
||
| − | *Whether the vocabulary the system recognize is small (in the order of tens or at most hundreds of words), or large (thousands of words). In the latter case, when the system is also continuous, it is commonly referred as '''large vocabulary speech recognition''' or '''LVCSR'''. |
||
| − | *The context of recognition - digits, names, free sentences, etc. |
||
| + | Front-End SR is where the provider dictates into a speech-recognition engine, the recognized words are displayed right after they are spoken, and the dictator is responsible for editing and signing off on the document. It never goes through an MT/editor. |
||
| ⚫ | |||
| + | Back-End SR or Deferred SR is where the provider dictates into a digital dictation system, and the voice is routed through a speech-recognition machine and the recognized draft document is routed along with the original voice file to the MT/editor, who edits the draft and finalizes the report. Deferred SR is being widely used in the industry currently. |
||
| − | Speech recognition systems, depending on several different factors, could have a wide performance range as measured by [[word error rate]]. These factors include the environment, the speaking rate of the speaker, the context (or the grammar) being used in recognition. |
||
| + | Many [[Emergency Medical Response]] (EMR) applications can be more effective and may be preformed more easily when deployed in conjunction with a speech-recognition engine. Searches, queries, and form filling may all be faster to perform by voice than by using a keyboard. |
||
| ⚫ | |||
| + | ===Military=== |
||
| − | Speaker-dependent dictation systems requiring a short period of training can capture continuous speech with a large vocabulary at normal pace with a very high accuracy. Most commercial companies claim that recognition software can achieve between 98% to 99% accuracy (getting one to two words out of one hundred wrong) if operated under optimal conditions. It should be noted that these optimal conditions usually means the test subjects have 1) matching speaker characteristics with the training data, 2) proper speaker adaptation, and 3) clean environment (e.g. office space). (This explains why some users, especially accented, might actually find that the recognition rate could be perceptually much lower than the expected 98% to 99%). |
||
| + | ====High-Performance Fighter Aircraft==== |
||
| + | Substantial efforts have been devoted in the last decade to the test and evaluation of speech recognition in fighter aircraft. Of particular note are the U.S. program in speech recognition for the Advanced Fighter Technology Integration (AFTI)/F-16 aircraft, the program in France on installing speech recognition systems on Mirage aircraft, and programs in the U.K. dealing with a variety of aircraft platforms. In these programs, speech recognizers have been operated successfully in fighter aircraft with applications including: setting radio frequencies, commanding an autopilot system, setting steer-point coordinates and weapons release parameters, and controlling flight displays. Generally, only very limited, constrained vocabularies have been used successfully, and a major effort has been devoted to integration of the speech recognizer with the avionics system. |
||
| + | Some important conclusions from the work are as follows: |
||
| ⚫ | |||
| + | 1. Speech recognition has definite potential for reducing pilot workload, but this potential was not realized consistently. |
||
| + | 2. Achievement of very high recognition accuracy (95% or more) was the most critical factor for making the speech recognition system useful - with lower recognition rates, pilots would not use the system. |
||
| + | 3. More natural vocabulary and grammar, and shorter training times would be useful, but only if very high recognition rates could be maintained. |
||
| + | Laboratory research in robust speech recognition for military environments has produced promising results which, if extendable to the cockpit, should improve the utility of speech recognition in high-performance aircraft. |
||
| − | ==Use== |
||
| + | Working with Swedish pilots flying in the JAS-39 Gripen cockpit, Englund (2004) found recognition deteriorated with increasing G-loads. It was also concluded that adaptation greatly improved the results in all cases and introducing models for breathing was shown to improve recognition scores significantly. Contrary to what might be expected, no effects of the broken English of the speakers were found. It was evident that spontaneous speech caused problems for the recognizer, as could be expected. A restricted vocabulary, and above all, a proper syntax, could thus be expected to improve recognition accuracy substantially. <ref> http://www.speech.kth.se/prod/publications/files/1664.pdf</ref> |
||
| − | {{Unbalanced|May 2006}} |
||
| + | ====Helicopters==== |
||
| − | Commercial systems for speech recognition have been available off-the-shelf since the [[1990s]]. Despite the apparent success of the technology, few people use such speech recognition systems on their [[desktop computers]]. It appears that most computer users can create and edit documents and interact with their computer more quickly with conventional input devices, a [[computer keyboard|keyboard]] and [[computer mouse|mouse]], despite the fact that most people are able to speak considerably faster than they can type. Using both keyboard and speech recognition simultaneously, however, can in some cases be more efficient than using any one of these inputs alone. A typical office environment, with a high amplitude of background speech, is one of the most adverse environments for current speech recognition technologies, and large-vocabulary systems with speaker-independence that are designed to operate within these adverse environments have significantly lower recognition accuracy. The typical achievable recognition rate [[as of 2005]] for large-vocabulary speaker-independent systems is about 80%-90% for a clear environment, but can be as low as 50% for scenarios like cellular phone with background noise. Additionally, heavy use of the speech organs can result in [[vocal loading]]. |
||
| + | The problems of achieving high recognition accuracy under stress and noise pertain strongly to the helicopter environment as well as to the fighter environment. The acoustic noise problem is actually more severe in the helicopter environment, not only because of the high noise levels but also because the helicopter pilot generally does not wear a facemask, which would reduce acoustic noise in the microphone. Substantial test and evaluation programs have been carried out in the post decade in speech recognition systems applications in helicopters, notably by the U.S. Army Avionics Research and Development Activity (AVRADA) and by the Royal Aerospace Establishment (RAE in the UK. Work in France has included speech recognition n the Puma helicopter. There has also been mush useful work in Canada. Results have been encouraging, and voice applications have included: control of communication radios; setting of navigation systems; and control of an automated target handover system. |
||
| + | As in fighter applications, the overriding issue for voice in helicopters is the impact on pilot effectiveness. Encouraging results are reported for the AVRADA tests, although these represent only a feasibility demonstration in a test environment. Much remains to be done both in speech recognition and in overall speech recognition technology, in order to consistently achieve performance improvements in operational settings. |
||
| − | Speech recognition systems have found use where the speed of text input is required to be extremely fast. They are used in legal and medical transcription, the generation of subtitles for live sports and current affairs programs on television; not directly but via an operator that re-speaks the dialog into software trained in the operator's voice; in such cases the operator also has special training, first to speak clearly and consistently to maximize recognition accuracy, second to indicate punctuation by various techniques, and also often domain-specific training (especially in medical or legal contexts where the operator needs to know specialized vocabulary and procedures). In courtrooms and similar situations where the operator's voice would disturb the proceedings, he or she may sit in a soundproofed booth or wear a [[Stenomask]] or similar device. |
||
| + | ====Battle Management==== |
||
| − | Speech recognition is sometimes a necessity for people who have difficulty interacting with their computers through a keyboard, for example, those with serious [[carpal tunnel syndrome]], impaired extremities, or other physical limitations. |
||
| + | Battle management command centres generally require rapid access to and control of large, rapidly changing information databases. Commanders and system operators need to query these databases as conveniently as possible, in an eyes-busy environment where much of the information is presented in a display format. Human machine interaction by voice has the potential to be very useful in these environments. A number of efforts have been undertaken to interface commercially available isolated-word recognizers into battle management environments. In one feasibility study, speech recognition equipment was tested in conjunction with an integrated information display for naval battle management applications. Users were very optimistic about the potential of the system, although capabilities were limited. |
||
| + | Speech understanding programs sponsored by the Defense Advanced Research Projects Agency (DARPA) in the U.S. has focussed on this problem of natural speech interface.. Speech recognition efforts have focussed on a database of continuous speech recognition (CSR), large-vocabulary speech which is designed to be representative of the naval resource management task. Significant advances in the state-of-the-art in CSR have been achieved, and current efforts are focussed on integrating speech recognition and natural language processing to allow spoken language interaction with a naval resource management system. |
||
| − | Speech recognition technology is used more and more for telephone applications like travel booking and information, financial account information, customer service call routing, and [[directory assistance]]. Using constrained grammar recognition (described below), such applications can achieve remarkably high accuracy. Research and development in speech recognition technology has continued to grow as the cost for implementing such voice-activated systems has dropped and the usefulness and efficiency of these systems has improved. For example, recognition systems optimized for telephone applications can often supply information about the confidence of a particular recognition, and if the confidence is low, it can trigger the application to prompt callers to confirm or repeat their request (for example "I heard you say 'billing', is that right?"). Furthermore, speech recognition has enabled the automation of certain applications that are not automatable using push-button interactive voice response (IVR) systems, like directory assistance and systems that allow callers to "dial" by speaking names listed in an electronic phone book. Nevertheless, speech recognition based systems remain the exception because push-button systems are still much cheaper to implement and operate.''' |
||
| + | ====Training Air Traffic Controllers==== |
||
| − | Speech recognition is also used for speech fluency evaluation and [http://www.readsay.com/llsrpc.html language instruction.] |
||
| + | Training for military (or civilian) air traffic controllers (ATC) represents an excellent application for speech recognition systems. Many ATC training systems currently require a person to act as a "pseudo-pilot", engaging in a voice dialog with the trainee controller, which simulates the dialog which the controller would have to conduct with pilots in a real ATC situation. |
||
| + | Speech recognition and synthesis techniques offer the potential to eliminate the need for a person to act as pseudo-pilot, thus reducing training and support personnel. Air controller tasks are also characterized by highly structured speech as the primary output of the controller, hence reducing the difficulty of the speech recognition task. |
||
| + | The U.S. Naval Training Equipment Center has sponsored a number of developments of prototype ATC trainers using speech recognition. Generally, the recognition accuracy falls short of providing graceful interaction between the trainee and the system. However, the prototype training systems have demonstrated a significant potential for voice interaction in these systems, and in other training applications. The U.S. Navy has sponsored a large-scale effort in ATC training systems, where a commercial speech recognition unit was integrated with a complex training system including displays and scenario creation. Although the recognizer was constrained in vocabulary, one of the goals of the training programs was to teach the controllers to speak in a constrained language, using specific vocabulary specifically designed for the ATC task. Research in France has focussed on the application of speech recognition in ATC training systems, directed at issues both in speech recognition and in application of task-domain grammar constraints. <ref>http://www.aclweb.org/anthology-new/H/H90/H90-1103.pdf</ref> |
||
| − | ==Noisy Channel Formulation of Statistical Speech Recognition== |
||
| − | Many modern approaches such as HMM-based and ANN-based speech recognition are based on noisy channel formulation (See also [[Alternative formulation of speech recognition]]. In that view, the task of a speech recognition system is to search for the most likely word sequence given the acoustic signal. In another words, the system is searching for the most likely word sequence <math> \tilde{W} </math> among all possible word sequences <math> W^* </math> from the acoustic signal <math> A </math> (or some will called '''observation sequence''' according to the [[Hidden Markov Model]] terminology) |
||
| + | ===Telephony and other domains=== |
||
| − | <math>\tilde{W} = arg max_{W \in W^*} \Pr(W | A) </math> |
||
| + | ASR in the field of telephony is now commonplace and in the field of computer gaming and simulation is becoming more widespread. Despite the high level of integration with word processing in general personal computing, however, ASR in the field of document production has not seen the expected increases in use. |
||
| ⚫ | |||
| − | Based on [[Bayes' rule]], the above formulation could be rewritten as |
||
| + | The performance of speech recognition systems is usually specified in terms of accuracy and speed. Accuracy may be measured in terms of Performance Accuracy which is usually rated with [[word error rate]], whereas speed is measured with the [[real time factor]]. Other measures of accuracy include [[Single Word Error Rate]] (SWER) and [[Command Success Rate]] (CSR). |
||
| ⚫ | |||
| − | <math> \tilde{W} = arg max_{W \in W^*} \frac{\Pr(A |W) \Pr(W)}{\Pr(A)} </math> |
||
| + | Commercially available speaker-dependent dictation systems usually require only a short period of training (sometimes also called `enrollment') and may successfully capture continuous speech with a large vocabulary at normal pace with a very high accuracy. Most commercial companies claim that recognition software can achieve between 98% to 99% accuracy if operated under optimal conditions. `Optimal conditions' usually assume that users: |
||
| − | Because the acoustic signal is common regardless of which word sequence chosen, the above could be usually simply to |
||
| + | * have speech characteristics which match the training data, |
||
| + | * can achieve proper speaker adaptation, and |
||
| + | * work in a clean noise environment (e.g. quiet office or laboratory space). |
||
| + | This explains why some users, especially those whose speech is heavily accented, might achieve recognition rates much lower than expected. Speech recognition in video has become a popular search technology used by several video search companies. |
||
| − | <math> \tilde{W} = arg max_{W \in W^*} \Pr(A |W) \Pr(W) </math> |
||
| ⚫ | |||
| − | The term <math> \Pr(A|W) </math> is generally called '''acoustic model'''. The term <math> \Pr(W) </math> is generally known as '''language model'''. |
||
| − | Both [[acoustic modeling]] and [[language modeling]] are important |
+ | Both [[acoustic modeling]] and [[language modeling]] are important parts of modern statistically-based speech recognition algorithms. Hidden Markov Models (HMM) are widely used in many systems. [[Language modeling]] has many other applications such as [[smart keyboard]] and [[document classification]] |
| + | [[Carnegie Mellon]] University has made much progress in increasing the speed of speech chips by using [[Application-specific_integrated_circuit|ASIC]]s (application-specific integrated circuits) and reconfigurable chips called [[Fpga|FPGA]]s (field programmable gate arrays). <ref>{{cite news | |
||
| ⚫ | |||
| + | url=http://www.axistive.com/computer-chips-to-enhance-speech-recognition.html | last=Dennis van der Heijden| title=Computer Chips to Enhance Speech Recognition| publisher=Axistive.com| date=[[2003-10-06]]}}</ref> |
||
| − | ===Hidden Markov |
+ | ===Hidden Markov model (HMM)-based speech recognition=== |
| − | Modern general-purpose speech recognition systems are generally based on [[ |
+ | Modern general-purpose speech recognition systems are generally based on [[Hidden Markov Model|HMMs]]. These are statistical models which output a sequence of symbols or quantities. |
| ⚫ | One possible reason why HMMs are used in speech recognition is that a speech signal could be viewed as a piecewise stationary signal or a short-time stationary signal. That is, one could assume in a short-time in the range of 10 milliseconds, speech could be approximated as a [[stationary process]]. Speech could thus be thought of as a [[Markov model]] for many stochastic processes. |
||
| ⚫ | Another reason why HMMs are popular is because they can be trained automatically and are simple and computationally feasible to use. In speech recognition, the hidden Markov model would output a sequence of ''n''-dimensional real-valued vectors (with ''n'' being a small integer, such as 10), outputting one of these every 10 milliseconds. The vectors would consist of [[cepstrum|cepstral]] coefficients, which are obtained by taking a [[Fourier transform]] of a short time window of speech and decorrelating the spectrum using a cosine transform, then taking the first (most significant) coefficients. The hidden Markov model will tend to have in each state a statistical distribution that is a mixture of diagonal covariance Gaussians which will give a likelihood for each observed vector. Each word, or (for more general speech recognition systems), each [[phoneme]], will have a different output distribution; a hidden Markov model for a sequence of words or phonemes is made by concatenating the individual trained hidden Markov models for the separate words and phonemes. |
||
| ⚫ | One possible reason why HMMs |
||
| + | Described above are the core elements of the most common, HMM-based approach to speech recognition. Modern speech recognition systems use various combinations of a number of standard techniques in order to improve results over the basic approach described above. A typical large-vocabulary system would need context dependency for the phonemes (so phonemes with different left and right context have different realizations as HMM states); it would use cepstral normalization to normalize for different speaker and recording conditions; for further speaker normalization it might use vocal tract length normalization (VTLN) for male-female normalization and maximum likelihood linear regression (MLLR) for more general speaker adaptation. The features would have so-called delta and delta-delta coefficients to capture speech dynamics and in addition might use heteroscedastic linear discriminant analysis (HLDA); or might skip the delta and delta-delta coefficients and use splicing and an LDA-based projection followed perhaps by heteroscedastic linear discriminant analysis or a global semitied covariance transform (also known as maximum likelihood linear transform, or MLLT). Many systems use so-called discriminative training techniques which dispense with a purely statistical approach to HMM parameter estimation and instead optimize some classification-related measure of the training data. Examples are maximum mutual information (MMI), minimum classification error (MCE) and minimum phone error (MPE). Sometimes they use a bivariant antidiscriminant Markov redundant inclusive group-oriented hidden computable commutative chain regression model in order to inductively forecast the semi-ring linear precomputed disparate computational models. |
||
| ⚫ | Another reason why HMMs are popular because they can be trained automatically and are simple and computationally feasible to use. In speech recognition |
||
| + | Decoding of the speech (the term for what happens when the system is presented with a new utterance and must compute the most likely source sentence) would probably use the [[Viterbi algorithm]] to find the best path, and here there is a choice between dynamically creating a combination hidden Markov model which includes both the acoustic and language model information, or combining it statically beforehand (the finite state transducer, or FST, approach). |
||
| − | {{cleanup-date|December 2005}} |
||
| ⚫ | |||
| − | The above is a very brief introduction to some of the more central aspects of speech recognition. Modern speech recognition systems use a host of standard techniques which it would be too time consuming to properly explain, but just to give a flavor, a typical large-vocabulary continuous system would probably have the following parts. It would need context dependency for the phones (so phones with different left and right context have different realizations); to handle unseen contexts it would need tree clustering of the contexts; it would of course use cepstral normalization to normalize for different recording conditions and depending on the length of time that the system had to adapt on different speakers and conditions it might use cepstral mean and variance normalization for channel differences, vocal tract length normalization (VTLN) for male-female normalization and maximum likelihood linear regression (MLLR) for more general speaker adaptation. The features would have delta and delta-delta coefficients to capture speech dynamics and in addition might use heteroscedastic linear discriminant analysis (HLDA); or might skip the delta and delta-delta coefficients and use LDA followed perhaps by heteroscedastic linear discriminant analysis or a global semitied covariance transform (also known as maximum likelihood linear transform (MLLT)). A serious company with a large amount of training data would probably want to consider discriminative training techniques like maximum mutual information (MMI), MPE, or (for short utterances) MCE, and if a large amount of speaker-specific enrollment data was available a more wholesale speaker adaptation could be done using MAP or, at least, tree-based maximum likelihood linear regression. Decoding of the speech (the term for what happens when the system is presented with a new utterance and must compute the most likely source sentence) would probably use the Viterbi algorithm to find the best path, but there is a choice between dynamically creating combination hidden Markov models which includes both the acoustic and language model information, or combining it statically beforehand (the [[AT&T]] approach, for which their FSM toolkit might be useful). Those who value their sanity might consider the AT&T approach, but be warned that it is memory hungry. |
||
| − | |||
| − | |||
| − | ===Neural Network-based Speech Recognition=== |
||
| − | |||
| − | {{cleanup-date|December 2005}} |
||
| − | |||
| − | Another approach in '''acoustic modeling''' is the use of [[Artificial neural networks|neural networks]]. They are capable of solving much more complicated recognition tasks, but do not scale as well as HMMs when it comes to large vocabularies. Rather than being used in general-purpose speech recognition applications they can handle low quality, noisy data and speaker independence. Such systems can achieve greater accuracy than HMM based systems, as long as there is training data and the vocabulary is limited. A more general approach using neural networks is phoneme recognition. This is an active field of research, but generally the results are better than for HMMs. There are also NN-HMM hybrid systems that use the neural network part for phoneme recognition and the hidden markov model part for language modeling. |
||
| − | |||
| ⚫ | |||
{{main|Dynamic time warping}} |
{{main|Dynamic time warping}} |
||
| + | Dynamic time warping is an approach that was historically used for speech recognition but has now largely been displaced |
||
| − | {{sectstub}} |
||
| + | by the more successful HMM-based approach. |
||
| + | Dynamic time warping is an algorithm for measuring similarity between two sequences which may vary in time or speed. For instance, similarities in walking patterns would be detected, even if in one video the person was walking slowly and if in another they were walking more quickly, or even if there were accelerations and decelerations during the course of one observation. DTW has been applied to video, audio, and graphics -- indeed, any data which can be turned into a linear representation can be analyzed with DTW. |
||
| + | A well known application has been automatic speech recognition, to cope with different speaking speeds. In general, it is a method that allows a computer to find an optimal match between two given sequences (e.g. time series) with certain restrictions, i.e. the sequences are "warped" non-linearly to match each other. This sequence alignment method is often used in the context of hidden Markov models. |
||
| − | ===Knowledge-based Speech Recognition === |
||
| − | {{sectstub}} |
||
| + | {{sect-stub}} |
||
| − | ===Current Research problems=== |
||
| ⚫ | |||
| − | * Speech recognition system are based on simplified stochastic models, so any aspects of the speech that may be important to recognition but are not represented in the models cannot be used to aid in recognition. |
||
| ⚫ | Popular speech recognition conferences held each year or two include ICASSP, Eurospeech/ICSLP (now named Interspeech) and the IEEE ASRU. Conferences in the field of [[Natural Language Processing]], such as ACL, NAACL, EMNLP, and HLT, are beginning to include papers on speech processing. Important journals include the [[IEEE]] Transactions on Speech and Audio Processing (now named [[IEEE]] Transactions on Audio, Speech and Language Processing), Computer Speech and Language, and Speech Communication. Books like "Fundamentals of Speech Recognition" by [[Lawrence Rabiner]] can be useful to acquire basic knowledge but may not be fully up to date (1993). Another good source can be "Statistical Methods for Speech Recognition" by Frederick Jelinek which is a more up to date book (1998). Even more up to date is "Computer Speech", by Manfred R. Schroeder, second edition published in 2004. A good insight into the techniques used in the best modern systems can be gained by paying attention to government sponsored competitions such as those organised by [[DARPA]] (the largest speech recognition-related project ongoing as of 2007 is the GALE project, which involves both speech recognition and translation components). |
||
| − | * [[Speech segmentation]], the division of the continuous speech signal into elementary units, is a very difficult problem. This task actually consists of two separate problems, the breakup and classification of the signal into a string of discrete "atomic" sounds ([[phoneme]]s), and the division of that string into into meaningful substrings ([[word]]s, or, more generally, [[lexical unit]]s). For most languages, the first task is already quite difficult — partly because of [[co-articulation]], which causes phonemes to interact or combine, even across word boundaries. The second task is not trivial either, because in normal spoken speech there are no pauses between words. An example, often quoted in the field, is the phrase ''how to wreck a nice beach'' — which, when spoken, sounds like ''How to recognize speech''. Proper segmentation therefore depends on context, syntax and semantics, meaning human knowledge and experience, and would thus require advanced [[pattern recognition]] and [[artificial intelligence]] technologies to be implemented on a computer. |
||
| − | * Intonation and sentence stress can play an important role in the interpretation of an utterance. As a simple example, utterances that might be transcribed as "go!", "go?" and "go." can clearly be recognized by a human, but determining which intonation corresponds to which punctuation is difficult for a computer. Most speech recognition systems are unable to provide any more information about an utterance other than what words were pronounced, so information about stress and intonation cannot be used by the application using the recognizer. Researchers are currently investigating emotion recognition, which may have practical applications. For example if a system detects anger or frustration, it can try asking different questions or forward the caller to a live operator. |
||
| − | * In a system designed for dictation, an ordinary spoken signal doesn't provide sufficient information to create a written form that obeys the normal rules for written language, such as punctuation and capitalization. These systems typically require the speaker to explicitly say where punctuation is to appear. |
||
| + | In terms of freely available resources, the [[HTK (software)|HTK]] book (and the accompanying HTK toolkit) is one place to start to both learn about speech recognition and to start experimenting. Another such resource is [[Carnegie Mellon University]]'s SPHINX toolkit. The AT&T libraries [http://www.research.att.com/projects/mohri/fsm FSM Library], [http://www.research.att.com/projects/mohri/grm GRM library], and [http://www.cs.nyu.edu/~mohri DCD library] are also general software libraries for large-vocabulary speech recognition. |
||
| − | ==Commercial Speech Recognition: A Survey of Market players== |
||
| + | A useful review of the area of robustness in ASR is provided by Junqua and Haton (1995). |
||
| − | {{advert|May 2006}} |
||
| + | ==Applications of speech recognition== |
||
| − | The challenge for developers of Automatic Speech Recognition (ASR) engines is that the end customer judges them on one criterion: did it understand what I said? That leaves little room for differentiation. Of course, there are areas like multi-language support, tuning tools, integration API (the proposed standard [[MRCP]] or proprietary) , etc., but recognition quality is most visible. Because of the complex algorithms and language models required to implement a high-quality speech recognition engine, it is both difficult for new companies to enter this market as well as difficult for existing vendors to maintain the necessary investment level to keep up and move ahead. |
||
| + | *Automatic translation |
||
| + | *Automotive speech recognition (e.g., [[Ford Sync]]) |
||
| + | *Court reporting (Realtime Voice Writing) |
||
| + | * Speech Biometric Recognition |
||
| + | *[[Hands-free computing]]: voice command recognition computer [[user interface]] |
||
| + | *[[Home automation]] |
||
| + | *[[Cockpit (aviation)]] (also termed [[Direct Voice Input]]) |
||
| + | *[[Interactive voice response]] |
||
| + | *[[Medical transcription]] |
||
| + | *[[Mobile telephony]], including mobile email. |
||
| + | *[[Pronunciation]] evaluation in computer-aided language learning applications |
||
| + | *[[Robotics]] |
||
| + | *[[Transcription]] (digital speech-to-text). |
||
| ⚫ | |||
| − | Currently, [[Nuance Communications]] (formerly known as ScanSoft) dominates the speech recognition market for server-based telephony and PC applications. There are several small vendors, like Aculab, Fonix Speech, Loquendo, LumenVox, Sensory Inc., Verbio, etc., but they are essentially niche players. Nuance's speech recognition business is actually composed of [[SpeechWorks]] and the products of several former niche players. [[IBM]] has also participated in the speech recognition engine market, but their [[ViaVoice]] product has gained traction primarily in the desktop command and control (grammar-constrained) and dictation markets. Nuance also makes Dragon [[NaturallySpeaking]], a desktop dictation system with theoretically possible recognition rates of up to 99 percent. In practice this is impossible to achieve, due to the fact that people use a vocabulary of over 300,000 words and these words have not all been put into the vocabulary of Naturally Speaking. |
||
| + | <div style="-moz-column-count:3; column-count:3;"> |
||
| + | * [[Audio mining]] |
||
| + | * [[Audio visual speech recognition]] |
||
| + | * [[Artificial intelligence]] |
||
| + | * [[Expert systems]] |
||
| ⚫ | |||
| + | * [[List of speech recognition projects]] |
||
| + | * [[Logogen model]] |
||
| + | * [[Microphone]] |
||
| ⚫ | |||
| + | * [[Automatic speaker identification]] |
||
| ⚫ | |||
| ⚫ | |||
| ⚫ | |||
| + | * [[Speech synthesis]] |
||
| + | * [[Speech verification]] |
||
| ⚫ | |||
| + | * [[Word error rate]] |
||
| + | </div> |
||
| + | == References == |
||
| − | [[Philips]] Speech Recognition Systems is the market leader in enterprise healthcare speech recognition systems with its flagship product SpeechMagic (according to a [http://www.frost.com/prod/servlet/press-release.pag?docid=54492494 report of Frost & Sullivan] of December 2005). SpeechMagic is installed in more than 7000 professional sites world-wide, supports 23 recognition languages and boasts a portfolio of more than 150 specialized recognition vocabularies. |
||
| + | *[http://citeseer.ist.psu.edu/392076.html "Survey of the State of the Art in Human Language Technology (1997) by Ron Cole et all"] |
||
| + | *[http://www.booksamillion.com/ncom/books?id=3954411806797&pid=0792396464 “Robustness in Automatic Speech Recognition - Fundamentals and Applications, (1995) by Junqua, J-C and Haton, J-P, Kluwer Academic Publishers.”] |
||
| − | For Mac users, [[iListen]] from [[MacSpeech]], Inc. is available. Based on the Philips speech engine, iListen has been shipping on the Mac since 2000. |
||
| + | <references /> |
||
| − | Speaker-independent speech recognition embedded for mobile phones is one of the fastest growing market segments. Grammar-based command and control and even dictation systems can now be purchased in mobile handsets from operators such as Cingular Wireless, Sprint PCS, Verizon Wireless, and Vodafone. [[Voicesignal]] is the dominant vendor in this rapidly growing segment. Microsoft, Nuance, and IBM have also announced intentions to enter this segment. |
||
| − | The big software heavyweights, [[Microsoft]] (Speech Server) and [[IBM]] (references - main site, voice toolkit preview, eWeek article, older InternetNews article, new InternetNews article on [[VXML]] toolkits) are now making substantial investments in speech recognition. IBM claims to have put one hundred speech researchers on the problem of taking ASR beyond the level of human speech recognition by [[2010]]. [[Bill Gates]] is also making very large investments in speech recognition research at Microsoft. At [[SpeechTEK]], Gates predicted that by [[2011]] the quality of ASR will catch up to human speech recognition. IBM and Microsoft are still well behind Nuance in market share. |
||
| − | |||
| − | |||
| − | Start-ups are also making an impact in speech recognition, most notably SimonSays Voice Technologies. A Toronto-based company, Simonsays has made several breakthroughs in robust server-based speech recognition. Though SimonSays currently possesses a smaller market share, they are certainly a company to watch. |
||
| − | |||
| − | Low cost speech recognition chip for toys and consumer electronics are supplied by Sensory Inc. and Extell Technologies. |
||
| − | |||
| ⚫ | |||
| ⚫ | Popular speech recognition conferences held each year or two include ICASSP, Eurospeech/ICSLP (now named Interspeech) and the IEEE ASRU. Conferences in the field of [[Natural Language Processing]], such as ACL, NAACL, EMNLP, and HLT, are beginning to include papers on speech processing. Important journals include the [[IEEE]] Transactions on Speech and Audio Processing (now named [[IEEE]] Transactions on Audio, Speech and Language Processing), |
||
| − | |||
| ⚫ | |||
| ⚫ | |||
| ⚫ | |||
| ⚫ | |||
| ⚫ | |||
| ⚫ | |||
| − | *[[VoiceXML]] |
||
==References & Bibliography== |
==References & Bibliography== |
||
| Line 145: | Line 164: | ||
==External links== |
==External links== |
||
| + | <!-- ATTENTION! Please do not add links without discussion and consensus on the talk page. Undiscussed links will be removed. As an alternative, you may add your website link to DMOZ, through which it will then be linked from this article via the template below. --> |
||
| − | *[http://SpeechWiki.org/ Speech Recognition wiki] |
||
| + | |||
| − | *[http://cmusphinx.sourceforge.net/ Sphinx Open Source Speech Recognition Engine] |
||
| + | *{{dmoz|Computers/Speech_Technology|Speech Technology}} |
||
| − | *[http://htk.eng.cam.ac.uk/ Entropic/Cambridge Hidden Markov Model Toolkit] |
||
| + | |||
| − | *[http://julius.sourceforge.jp/en/julius.html Julius Open Source Speech Recognition Engine] |
||
| − | *[http://www.icsi.berkeley.edu/~dpwe/projects/sprach/sprachcore.html The Sphracore software packages] |
||
| − | *[http://sourceforge.net/projects/opencvlibrary/ Open CV library, especially the multi-stream speech and vision combination programs] |
||
| − | *[http://xvoice.sourceforge.net/ Xvoice: Speech control of X applications] |
||
| − | *[http://future.wikicities.com/wiki/Speech_recognition Future implications of speech recognition] at Future Wiki |
||
| − | *[http://www.andybrain.com/extras/voice_recognition.htm Voice recognition software review] |
||
| − | *[http://www.talkingdesktop.com Speech Recognition software for the desktop] |
||
| − | *[http://speech.even-zohar.com Review of SR software, including Microsoft SR and a list of supported languages] |
||
| − | *[http://www.elsevier.com/wps/find/journaldescription.cws_home/505597/description Speech Communication journal] |
||
| − | *[http://www.aurix.com/ Aurix speech recognition software] |
||
| − | {{Technology}} |
||
[[Category:Computational linguistics]] |
[[Category:Computational linguistics]] |
||
[[Category:Speech recognition]] |
[[Category:Speech recognition]] |
||
| + | [[Category:Human computer interface]] |
||
| − | |||
| + | <!-- |
||
| + | [[cs:Rozpoznávání řeči]] |
||
| + | [[da:Talegenkendelse]] |
||
| + | [[de:Spracherkennung]] |
||
| + | [[el:Αναγνώριση Ομιλίας]] |
||
| + | [[es:Reconocimiento del habla]] |
||
| + | [[eu:Hizketaren ezagutza]] |
||
| + | [[fa:تشخیص گفتار]] |
||
| + | [[fr:Reconnaissance vocale]] |
||
| + | [[gl:Recoñecemento da fala]] |
||
| + | [[ko:음성 인식]] |
||
| + | [[it:Riconoscimento vocale]] |
||
| + | [[nl:Spraakherkenning]] |
||
| + | [[ja:音声認識]] |
||
| + | [[pl:Rozpoznawanie mowy]] |
||
| + | [[pt:Reconhecimento de fala]] |
||
| + | [[sk:Rozpoznávanie reči]] |
||
| + | [[sr:Препознавање говора]] |
||
| + | [[fi:Puheentunnistus]] |
||
| + | [[sv:Taligenkänning]] |
||
| + | [[th:การรู้จำคำพูด]] |
||
| + | [[vi:Nhận dạng tiếng nói]] |
||
| + | [[zh:语音识别]] |
||
| + | --> |
||
{{enWP|Speech recognition}} |
{{enWP|Speech recognition}} |
||
Revision as of 18:15, 13 October 2013
Assessment |
Biopsychology |
Comparative |
Cognitive |
Developmental |
Language |
Individual differences |
Personality |
Philosophy |
Social |
Methods |
Statistics |
Clinical |
Educational |
Industrial |
Professional items |
World psychology |
Language: Linguistics · Semiotics · Speech
Speech recognition (in many contexts also known as automatic speech recognition, computer speech recognition or erroneously as voice recognition) is the process of converting a speech signal to a sequence of words in the form of digital data, by means of an algorithm implemented as a computer program.
Speech recognition applications that have emerged over the last few is years include voice dialing (e.g., "Call home"), call routing (e.g., "I would like to make a collect call"), domotic appliance control and content-based spoken audio search (e.g. find a podcast where particular words were spoken), simple data entry (e.g., entering a credit card number), preparation of structured documents (e.g., a radiology report), speech-to-text processing (text for OpenDocument, word processors, emails...); in the cockpit of some military fast jets (where it is generally referred to as Direct Voice Input - DVI -).
Voice recognition, or better, speaker recognition is a related process that attempts to identify the person speaking, as opposed to what is being said.
History
One of the most notable domains for the commercial application of speech recognition in the United States has been health care and in particular the work of the medical transcriptionist (MT). According to industry experts, at its inception, speech recognition (SR) was sold as a way to completely eliminate transcription rather than make the transcription process more efficient, hence it was not accepted. It was also the case that SR at that time was often technically deficient. Additionally, to be used effectively, it changes to the ways physicians worked and documented clinical encounters, which many if not all were reluctant to do. The biggest limitation to speech recognition automating transcription, however, is seen as the software. The nature of narrative dictation is highly interpretive and often requires judgment that may be provided by a real human but not by an automated system. Another limitation has been the extensive amount of time required by the user and/or system provider to train the software.
A useful distinction in ASR is often made between "artificial syntax systems" which are usually domain specific and "natural language processing" which are usually language specific. Each of these types of application present their own particular goals and challenges.
Current
Health Care
In the health care domain, even in the wake of improving speech recognition technologies, medical transcriptionists (MTs) have not yet become obsolete. Many experts in the field anticipate that with increased use of speech recognition technology, the services provided may be redistributed rather than replaced. Speech recognition has not yet made the skills of MTs obsolete.
Speech recognition can be implemented in front-end or back-end of the medical documentation process.
Front-End SR is where the provider dictates into a speech-recognition engine, the recognized words are displayed right after they are spoken, and the dictator is responsible for editing and signing off on the document. It never goes through an MT/editor.
Back-End SR or Deferred SR is where the provider dictates into a digital dictation system, and the voice is routed through a speech-recognition machine and the recognized draft document is routed along with the original voice file to the MT/editor, who edits the draft and finalizes the report. Deferred SR is being widely used in the industry currently.
Many Emergency Medical Response (EMR) applications can be more effective and may be preformed more easily when deployed in conjunction with a speech-recognition engine. Searches, queries, and form filling may all be faster to perform by voice than by using a keyboard.
Military
High-Performance Fighter Aircraft
Substantial efforts have been devoted in the last decade to the test and evaluation of speech recognition in fighter aircraft. Of particular note are the U.S. program in speech recognition for the Advanced Fighter Technology Integration (AFTI)/F-16 aircraft, the program in France on installing speech recognition systems on Mirage aircraft, and programs in the U.K. dealing with a variety of aircraft platforms. In these programs, speech recognizers have been operated successfully in fighter aircraft with applications including: setting radio frequencies, commanding an autopilot system, setting steer-point coordinates and weapons release parameters, and controlling flight displays. Generally, only very limited, constrained vocabularies have been used successfully, and a major effort has been devoted to integration of the speech recognizer with the avionics system.
Some important conclusions from the work are as follows: 1. Speech recognition has definite potential for reducing pilot workload, but this potential was not realized consistently. 2. Achievement of very high recognition accuracy (95% or more) was the most critical factor for making the speech recognition system useful - with lower recognition rates, pilots would not use the system. 3. More natural vocabulary and grammar, and shorter training times would be useful, but only if very high recognition rates could be maintained.
Laboratory research in robust speech recognition for military environments has produced promising results which, if extendable to the cockpit, should improve the utility of speech recognition in high-performance aircraft.
Working with Swedish pilots flying in the JAS-39 Gripen cockpit, Englund (2004) found recognition deteriorated with increasing G-loads. It was also concluded that adaptation greatly improved the results in all cases and introducing models for breathing was shown to improve recognition scores significantly. Contrary to what might be expected, no effects of the broken English of the speakers were found. It was evident that spontaneous speech caused problems for the recognizer, as could be expected. A restricted vocabulary, and above all, a proper syntax, could thus be expected to improve recognition accuracy substantially. [1]
Helicopters
The problems of achieving high recognition accuracy under stress and noise pertain strongly to the helicopter environment as well as to the fighter environment. The acoustic noise problem is actually more severe in the helicopter environment, not only because of the high noise levels but also because the helicopter pilot generally does not wear a facemask, which would reduce acoustic noise in the microphone. Substantial test and evaluation programs have been carried out in the post decade in speech recognition systems applications in helicopters, notably by the U.S. Army Avionics Research and Development Activity (AVRADA) and by the Royal Aerospace Establishment (RAE in the UK. Work in France has included speech recognition n the Puma helicopter. There has also been mush useful work in Canada. Results have been encouraging, and voice applications have included: control of communication radios; setting of navigation systems; and control of an automated target handover system.
As in fighter applications, the overriding issue for voice in helicopters is the impact on pilot effectiveness. Encouraging results are reported for the AVRADA tests, although these represent only a feasibility demonstration in a test environment. Much remains to be done both in speech recognition and in overall speech recognition technology, in order to consistently achieve performance improvements in operational settings.
Battle Management
Battle management command centres generally require rapid access to and control of large, rapidly changing information databases. Commanders and system operators need to query these databases as conveniently as possible, in an eyes-busy environment where much of the information is presented in a display format. Human machine interaction by voice has the potential to be very useful in these environments. A number of efforts have been undertaken to interface commercially available isolated-word recognizers into battle management environments. In one feasibility study, speech recognition equipment was tested in conjunction with an integrated information display for naval battle management applications. Users were very optimistic about the potential of the system, although capabilities were limited.
Speech understanding programs sponsored by the Defense Advanced Research Projects Agency (DARPA) in the U.S. has focussed on this problem of natural speech interface.. Speech recognition efforts have focussed on a database of continuous speech recognition (CSR), large-vocabulary speech which is designed to be representative of the naval resource management task. Significant advances in the state-of-the-art in CSR have been achieved, and current efforts are focussed on integrating speech recognition and natural language processing to allow spoken language interaction with a naval resource management system.
Training Air Traffic Controllers
Training for military (or civilian) air traffic controllers (ATC) represents an excellent application for speech recognition systems. Many ATC training systems currently require a person to act as a "pseudo-pilot", engaging in a voice dialog with the trainee controller, which simulates the dialog which the controller would have to conduct with pilots in a real ATC situation. Speech recognition and synthesis techniques offer the potential to eliminate the need for a person to act as pseudo-pilot, thus reducing training and support personnel. Air controller tasks are also characterized by highly structured speech as the primary output of the controller, hence reducing the difficulty of the speech recognition task.
The U.S. Naval Training Equipment Center has sponsored a number of developments of prototype ATC trainers using speech recognition. Generally, the recognition accuracy falls short of providing graceful interaction between the trainee and the system. However, the prototype training systems have demonstrated a significant potential for voice interaction in these systems, and in other training applications. The U.S. Navy has sponsored a large-scale effort in ATC training systems, where a commercial speech recognition unit was integrated with a complex training system including displays and scenario creation. Although the recognizer was constrained in vocabulary, one of the goals of the training programs was to teach the controllers to speak in a constrained language, using specific vocabulary specifically designed for the ATC task. Research in France has focussed on the application of speech recognition in ATC training systems, directed at issues both in speech recognition and in application of task-domain grammar constraints. [2]
Telephony and other domains
ASR in the field of telephony is now commonplace and in the field of computer gaming and simulation is becoming more widespread. Despite the high level of integration with word processing in general personal computing, however, ASR in the field of document production has not seen the expected increases in use.
Performance of speech recognition systems
The performance of speech recognition systems is usually specified in terms of accuracy and speed. Accuracy may be measured in terms of Performance Accuracy which is usually rated with word error rate, whereas speed is measured with the real time factor. Other measures of accuracy include Single Word Error Rate (SWER) and Command Success Rate (CSR).
Most speech recognition users would tend to agree that dictation machines can achieve very high performance in controlled conditions. There is some confusion, however, over the interchangeability of the terms "speech recognition" and "dictation".
Commercially available speaker-dependent dictation systems usually require only a short period of training (sometimes also called `enrollment') and may successfully capture continuous speech with a large vocabulary at normal pace with a very high accuracy. Most commercial companies claim that recognition software can achieve between 98% to 99% accuracy if operated under optimal conditions. `Optimal conditions' usually assume that users:
- have speech characteristics which match the training data,
- can achieve proper speaker adaptation, and
- work in a clean noise environment (e.g. quiet office or laboratory space).
This explains why some users, especially those whose speech is heavily accented, might achieve recognition rates much lower than expected. Speech recognition in video has become a popular search technology used by several video search companies.
Limited vocabulary systems, requiring no training, can recognize a small number of words (for instance, the ten digits) as spoken by most speakers. Such systems are popular for routing incoming phone calls to their destinations in large organizations.
Both acoustic modeling and language modeling are important parts of modern statistically-based speech recognition algorithms. Hidden Markov Models (HMM) are widely used in many systems. Language modeling has many other applications such as smart keyboard and document classification
Carnegie Mellon University has made much progress in increasing the speed of speech chips by using ASICs (application-specific integrated circuits) and reconfigurable chips called FPGAs (field programmable gate arrays). [3]
Hidden Markov model (HMM)-based speech recognition
Modern general-purpose speech recognition systems are generally based on HMMs. These are statistical models which output a sequence of symbols or quantities. One possible reason why HMMs are used in speech recognition is that a speech signal could be viewed as a piecewise stationary signal or a short-time stationary signal. That is, one could assume in a short-time in the range of 10 milliseconds, speech could be approximated as a stationary process. Speech could thus be thought of as a Markov model for many stochastic processes.
Another reason why HMMs are popular is because they can be trained automatically and are simple and computationally feasible to use. In speech recognition, the hidden Markov model would output a sequence of n-dimensional real-valued vectors (with n being a small integer, such as 10), outputting one of these every 10 milliseconds. The vectors would consist of cepstral coefficients, which are obtained by taking a Fourier transform of a short time window of speech and decorrelating the spectrum using a cosine transform, then taking the first (most significant) coefficients. The hidden Markov model will tend to have in each state a statistical distribution that is a mixture of diagonal covariance Gaussians which will give a likelihood for each observed vector. Each word, or (for more general speech recognition systems), each phoneme, will have a different output distribution; a hidden Markov model for a sequence of words or phonemes is made by concatenating the individual trained hidden Markov models for the separate words and phonemes.
Described above are the core elements of the most common, HMM-based approach to speech recognition. Modern speech recognition systems use various combinations of a number of standard techniques in order to improve results over the basic approach described above. A typical large-vocabulary system would need context dependency for the phonemes (so phonemes with different left and right context have different realizations as HMM states); it would use cepstral normalization to normalize for different speaker and recording conditions; for further speaker normalization it might use vocal tract length normalization (VTLN) for male-female normalization and maximum likelihood linear regression (MLLR) for more general speaker adaptation. The features would have so-called delta and delta-delta coefficients to capture speech dynamics and in addition might use heteroscedastic linear discriminant analysis (HLDA); or might skip the delta and delta-delta coefficients and use splicing and an LDA-based projection followed perhaps by heteroscedastic linear discriminant analysis or a global semitied covariance transform (also known as maximum likelihood linear transform, or MLLT). Many systems use so-called discriminative training techniques which dispense with a purely statistical approach to HMM parameter estimation and instead optimize some classification-related measure of the training data. Examples are maximum mutual information (MMI), minimum classification error (MCE) and minimum phone error (MPE). Sometimes they use a bivariant antidiscriminant Markov redundant inclusive group-oriented hidden computable commutative chain regression model in order to inductively forecast the semi-ring linear precomputed disparate computational models.
Decoding of the speech (the term for what happens when the system is presented with a new utterance and must compute the most likely source sentence) would probably use the Viterbi algorithm to find the best path, and here there is a choice between dynamically creating a combination hidden Markov model which includes both the acoustic and language model information, or combining it statically beforehand (the finite state transducer, or FST, approach).
Dynamic time warping (DTW)-based speech recognition
- Main article: Dynamic time warping
Dynamic time warping is an approach that was historically used for speech recognition but has now largely been displaced by the more successful HMM-based approach. Dynamic time warping is an algorithm for measuring similarity between two sequences which may vary in time or speed. For instance, similarities in walking patterns would be detected, even if in one video the person was walking slowly and if in another they were walking more quickly, or even if there were accelerations and decelerations during the course of one observation. DTW has been applied to video, audio, and graphics -- indeed, any data which can be turned into a linear representation can be analyzed with DTW.
A well known application has been automatic speech recognition, to cope with different speaking speeds. In general, it is a method that allows a computer to find an optimal match between two given sequences (e.g. time series) with certain restrictions, i.e. the sequences are "warped" non-linearly to match each other. This sequence alignment method is often used in the context of hidden Markov models.
For further information
Popular speech recognition conferences held each year or two include ICASSP, Eurospeech/ICSLP (now named Interspeech) and the IEEE ASRU. Conferences in the field of Natural Language Processing, such as ACL, NAACL, EMNLP, and HLT, are beginning to include papers on speech processing. Important journals include the IEEE Transactions on Speech and Audio Processing (now named IEEE Transactions on Audio, Speech and Language Processing), Computer Speech and Language, and Speech Communication. Books like "Fundamentals of Speech Recognition" by Lawrence Rabiner can be useful to acquire basic knowledge but may not be fully up to date (1993). Another good source can be "Statistical Methods for Speech Recognition" by Frederick Jelinek which is a more up to date book (1998). Even more up to date is "Computer Speech", by Manfred R. Schroeder, second edition published in 2004. A good insight into the techniques used in the best modern systems can be gained by paying attention to government sponsored competitions such as those organised by DARPA (the largest speech recognition-related project ongoing as of 2007 is the GALE project, which involves both speech recognition and translation components).
In terms of freely available resources, the HTK book (and the accompanying HTK toolkit) is one place to start to both learn about speech recognition and to start experimenting. Another such resource is Carnegie Mellon University's SPHINX toolkit. The AT&T libraries FSM Library, GRM library, and DCD library are also general software libraries for large-vocabulary speech recognition.
A useful review of the area of robustness in ASR is provided by Junqua and Haton (1995).
Applications of speech recognition
- Automatic translation
- Automotive speech recognition (e.g., Ford Sync)
- Court reporting (Realtime Voice Writing)
- Speech Biometric Recognition
- Hands-free computing: voice command recognition computer user interface
- Home automation
- Cockpit (aviation) (also termed Direct Voice Input)
- Interactive voice response
- Medical transcription
- Mobile telephony, including mobile email.
- Pronunciation evaluation in computer-aided language learning applications
- Robotics
- Transcription (digital speech-to-text).
See also
- Audio mining
- Audio visual speech recognition
- Artificial intelligence
- Expert systems
- Keyword spotting
- List of speech recognition projects
- Logogen model
- Microphone
- Speech Analytics
- Automatic speaker identification
- Speech corpus
- Speech perception
- Speech processing
- Speech synthesis
- Speech verification
- Windows Speech Recognition
- Word error rate
References
- ↑ http://www.speech.kth.se/prod/publications/files/1664.pdf
- ↑ http://www.aclweb.org/anthology-new/H/H90/H90-1103.pdf
- ↑ includeonly>Dennis van der Heijden. "Computer Chips to Enhance Speech Recognition", Axistive.com, 2003-10-06.
References & Bibliography
Key texts
Books
Papers
Additional material
Books
Papers
External links
| This page uses Creative Commons Licensed content from Wikipedia (view authors). |