Accession Number : ADA298901

Title :   Robust Continuous Speech Recognition.

Descriptive Note : Final rept. 25 Mar 91-30 Jun 95,

Corporate Author : BBN SYSTEMS AND TECHNOLOGIES CORP CAMBRIDGE MA

Personal Author(s) : Makhoul, J. ; Schwartz, R.

PDF Url : ADA298901

Report Date : SEP 1994

Pagination or Media Count : 50

Abstract : The objective of this basic research is to develop accurate and detailed mathematical models of the fundamental units of speech (phonemes) for large-vocabulary continuous speech recognition. The important goals of this work are to achieve the highest possible word recognition accuracy in continuous speech and to develop methods for the rapid adaptation of phonetic models to the voice of a new speaker.

Descriptors :   *SPEECH RECOGNITION, *PATTERN RECOGNITION, DATA BASES, MATHEMATICAL MODELS, ALGORITHMS, SOFTWARE ENGINEERING, NEURAL NETS, OPTIMIZATION, REAL TIME, ACCURACY, LEARNING MACHINES, ADAPTIVE SYSTEMS, SPEECH ANALYSIS, VOCABULARY, MATCHING, MICROPHONES, ACOUSTIC DATA, MARKOV PROCESSES, NATURAL LANGUAGE, DECODERS, WORD RECOGNITION, PHONETICS, ERROR DETECTION CODES, PHONEMES.

Subject Categories : Linguistics
      Cybernetics
      Voice Communications

Distribution Statement : APPROVED FOR PUBLIC RELEASE