Speech recognition

Categories: Wikipedia section cleanup | Computational linguistics | Speech recognition

Speech recognition technologies allow computers equipped with a source of sound input, such as a microphone, to interpret human speech, for example, for transcription or as an alternative method of interacting with a computer.

1 Classification
2 Use
3 Approaches
4 Technical issues
5 Market players
6 For further information
7 See also
8 External links
9 community and open-source resources
10 telephony/server-side speech recognition

[edit]

Classification

Such systems can be classified as to

Whether they require the user to "train" the system to recognise their own particular speech patterns or not.
Whether the system is trained for one user only or is speaker independent.
Whether the system can recognise continuous speech or requires users to break up their speech into discrete words.
Whether the system is intended for clear speech material, or is designed to operate on distorted transfer channels (e.g., cellular telephones) and possibly background noise or other speaker talking simultaneously.
Whether the vocabulary the system recognises is small (in the order of tens or at most hundreds of words), or large (thousands of words).
The context of recognition - digits, names, free sentences, commands.

Speaker-dependent systems requiring a short amount of training can capture continuous speech with a large vocabulary at normal pace with an accuracy of about 98% (getting two words in one hundred wrong) if operated under optimal conditions, and different systems that require no training can recognize a small number of words (for instance, the ten digits of the decimal system) as spoken by most speakers. Such systems are popular for routing incoming phone calls to their destinations in large organisations.

[edit]

Use

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 keyboard and 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.

Speech recognition systems have found use where the speed of text input is required to be extremely fast. They are used in 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 operators voice.

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, damaged hands or arms, or other physical limitations.

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 efficacy 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.

[edit]

Approaches

The two most common approaches used to recognize a speaker’s response are often called grammar constrained recognition and natural language recognition. When ASR (automatic speech recognition) is used to transcribe speech, it is commonly called dictation.

[edit]

Technical issues

This section needs to be cleaned up to conform to a higher standard of article quality. After the section has been cleaned up, you may remove this message. For help, see Wikipedia:How to edit a page and the Category:Wikipedia help.

Modern speech recognition systems are generally based on hidden Markov models (HMMs). This is a statistical model which outputs a sequence of symbols or quantities. Having a model which gives us the probability of an observed sequence of acoustic data given one or another word (or word sequence) will enable us to work out the most likely word sequence by the application of Bayes' rule:

<math>\Pr(\mathrm{word} \mid \mathrm{acoustics}) = \frac{\Pr(\mathrm{acoustics} \mid \mathrm{word}) \Pr(\mathrm{word})}{\Pr(\mathrm{acoustics})}.</math>

For a given sequence of acoustic data (think Wave file), Pr(acoustics) is a constant and can be ignored. Pr(word) is the prior probability of the word, obtained through language modeling (a science in itself; suffice it to say that Pr(mushroom soup) > Pr(much rooms hope)); Pr(acoustics|word) is the most involved term on the right hand side of the equation and is obtained from the aforementioned hidden Markov models.

Hidden Markov models are popular because they can be trained automatically and are simple and computationally feasible to use. In speech recognition, to give the very simplest setup possible, the hidden Markov model would output a sequence of n-dimensional real-valued vectors with n around, say, 13, outputting one of these every 100 milliseconds. The vectors, again in the very simplest case, 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 called a mixture of diagonal 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.

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.

Some other key technical problems in speech recognition are:

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.
Co-articulation of phonemes and words, depending on the input language, can make the task of speech recognition considerably more difficult. In some languages, like English, co-articulatory effects are extensive and far-reaching, meaning that the expected phonetic signal of a whole utterance can be vastly different than a simple concatenation of the expected phonetic signal of each sound or word. Consider for example the sentence "what are you going to do?", which when spoken might sound like "whatchagonnado?", which has a phonetic signal which is very different from the expected phonetic signal of each word separately.
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 from 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 naturally spoken language, there are no pauses between words, so it is difficult for a computer to decide where word boundaries lie. Some sets of utterances can sound the same, but can only be disambiguated by an appeal to context: one famous T-shirt worn by Apple Computer researchers made this point: I helped Apple wreck a nice beach, which, when spoken, sounds like I helped Apple recognize speech. Using common sense and context to disambiguate cases like this can be considered a separate field of inquiry: natural language understanding. A general solution of many of the above problems effectively requires human knowledge and experience, and would thus require advanced pattern recognition and artificial intelligence technologies to be implemented on a computer. In particular, statistical language models are often employed for disambiguation and improvement of the recognition accuracies.

[edit]

Market players

The challenge for developers of 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.

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.

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.

This is all changing. 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.

[edit]

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, Computer Speech and Language, and Speech Communications. Books like "Fundamentals of Speech Recognition" by Lawrence Rabiner can be useful to acquire basic knowledge but may not be fully up to date. Keep an eye on government sponsored competitions such as those organised by DARPA (the telephone speech evaluation was most recently known as Rich Transcription). 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 (if you are very brave). You could also search for Carnegie Mellon University's SPHINX toolkit.

[edit]