speech recognition

(redirected from Speech recognizer)
Also found in: Dictionary, Encyclopedia.

speech recognition

Speech understanding, voice recognition Informatics The ability of a computer, through software, to accept spoken words as dictation or follow voice commands

speech rec·og·ni·tion

(spēch rek'ŏg-nish'ŭn)
Software program used by some medical transcription departments to translate spoken language into a draft printed format that is then edited by medical transcriptionists to create a permanent record of patient care.
Synonym(s): voice recognition.

speech recognition

The ability of a machine or computer to interpret human speech. Also known as voice recognition and speech understanding.
References in periodicals archive ?
Spanish language recognizer implemented in Windows'8 operation system (Microsoft Speech Recognizer 8.0 (Spanish-US)) (REC_SP) was chosen for adaptation process to the Lithuanian language recognition.
The metric of performance of the speech recognizers was the word recognition accuracy (see (9)).
Normally, running a speech recognizer on audio recordings doesn't produce a highly accurate transcript because speech-recognition systems have difficulty if they haven't been trained for a particular speaker or if the speech is continuous.
Participants in pilot experiments had some difficulty adapting to the use of the speech recognizer. Their difficulties were exacerbated if the error rate of the recognizer was so high that they were continually involved in correction and retraining.
For this evaluation, systems were provided with much larger amounts of training and test data and with word transcripts generated by an automatic speech recognizer. Speaker detection performance was evaluated by measuring the correctness of detection decisions by the systems.
Instead, the program runs it through a speech recognizer using that doctor's acoustic and language profile, and out the other end comes a document that is typically 90-plus percent accurate.
The Philips VoCon speech recognizer for embedded systems has been integrated into various consumer electronics products and devices.
Programmed to modify itself according to whatever signals come into the system, the speech recognizer actually "learns" how to identify sounds and words.
The CD-HMM based speech recognizer was used as the preferred selection for proprietary Lithuanian speech recognizer since it has shown that such model is the most efficient one in wide variety of applications.
(2009), disfluencies are not specifically handled, but if a parse fails, the speech recognizer output is passed to the goal manager as a bag of words.
Voice solutions provider Spoken Communications supports a hybrid architecture in which the speech recognizer is backed up by a human who can monitor four or more interactions at once.

Full browser ?