Accession Number:

ADA230126

Title:

Improvements in the BYBLOS Continuous Speech Recognition System

Descriptive Note:

Final rept. 18 Jan 1988-30 Sep 1990

Corporate Author:

BBN SYSTEMS AND TECHNOLOGIES CORP CAMBRIDGE MA

Personal Author(s):

• Schwartz, R.
• Austin, S.
• Barry, C.
• Kubala, F.
• Makhoul, J.

Report Date:

1990-11-01

Pagination or Media Count:

57.0

Abstract:

The objective of this research was to develop accurate mathematical models of speech sounds for the purpose of large-vocabulary continuous speech recognition. The research focussed on three areas developing better speech models to improve recognition accuracy, exploring new techniques for speaker-independent training, and developing speaker adaptation techniques that allow system use with a minimum of training. The work was performed within the BBN BYBLOS speech recognition system, which is based on the use of phonetic hidden Markov models. As a result of several model improvements, we have succeeded in decreasing the word rate by a factor of four for speaker-dependent and speaker- independent recognition. In speaker-independent recognition, we developed a new training paradigm in which we record speech from only a dozen speakers instead of the traditional approach of recording more than a hundred speakers. The same approach has been shown to be useful for effective speaker adaptation with only two minutes of speech training.

Descriptors:

• *MATHEMATICAL MODELS
• TRAINING
• RATES
• ACCURACY
• SOUND
• MARKOV PROCESSES
• WORDS(LANGUAGE)
• SPEECH RECOGNITION
• RECORDING SYSTEMS
• SPEECH
• ADAPTATION
• MODELS
• RECOGNITION

Subject Categories:

• Cybernetics
• Voice Communications

Distribution Statement:

APPROVED FOR PUBLIC RELEASE