speech recognition

(redirected from Speech-to-text)
Also found in: Dictionary, Medical.

speech recognition

[′spēch ‚rek·ig′nish·ən]
(engineering acoustics)
The process of analyzing an acoustic speech signal to identify the linguistic message that was intended, so that a machine can correctly respond to spoken commands.

speech recognition

(application)
(Or voice recognition) The identification of spoken words by a machine. The spoken words are digitised (turned into sequence of numbers) and matched against coded dictionaries in order to identify the words.

Most systems must be "trained," requiring samples of all the actual words that will be spoken by the user of the system. The sample words are digitised, stored in the computer and used to match against future words. More sophisticated systems require voice samples, but not of every word. The system uses the voice samples in conjunction with dictionaries of larger vocabularies to match the incoming words. Yet other systems aim to be "speaker-independent", i.e. they will recognise words in their vocabulary from any speaker without training.

Another variation is the degree with which systems can cope with connected speech. People tend to run words together, e.g. "next week" becomes "neksweek" (the "t" is dropped). For a voice recognition system to identify words in connected speech it must take into account the way words are modified by the preceding and following words.

It has been said (in 1994) that computers will need to be something like 1000 times faster before large vocabulary (a few thousand words), speaker-independent, connected speech voice recognition will be feasible.
References in periodicals archive ?
patent, "Method and System for Providing Automated Captioning for AV Signals," expands ENCO's intellectual property for captioning technology and methods that help broadcasters and professional AV customers, including those in corporate, education, government and venues, automate and accelerate speech-to-text translation to deliver open or closed captions.
The feature is a mix of two capabilities - speech-to-text and text-to-speech.
CEA's research also found consumer preference for speech-to-text is slightly higher than text-to-speech; 34 percent of respondents expressed an interest in speech-to-text versus 29 percent for text-to-speech.
Mindshare converts all that ranting and raving into text using accurate speech-to-text technology, transcribing the comments and saving them for easy recall.
Voice-to-content services provider SpinVox announced on Wednesday the availability of new speech-to-text conversion capabilities in the Nortel CallPilot Unified Messaging portfolio.
Even with the rough edges, speech-to-text software has tremendous growth opportunity.
Speech-to-text can be used to recognize the spoken word of the original lecturer, or recognize the words of a "parrot" in the original language.
The combination of eZiText and eZiType text-prediction and TravellingWave's predictive speech-to-text technology is expected to enable VoicePredict to deliver greater value for texting.
Voicemail management in the enterprise just got easier with the availability of new speech-to-text conversion capabilities in the Nortel CallPilot Unified Messaging portfolio.
Based on Lucent's technologies, Vocal Link's system will allow any message to be transmitted or received by voice, e-mail, fax, pager or wireless device using text-to-speech and speech-to-text conversion.
In addition to helping create the voice-to-content category, Daniel has also been an avid supporter for creating universal standards for quality that will help propel speech-to-text category success with consistent, high-quality end-user experiences across carrier, VoIP, Unified Communications and Web 2.
Leading Machine-Based Speech-to-Text Platform to Enhance Voice Interface of the Industry's Most Comprehensive Memory Service