Accession Number : ADA299910

Title :   A Robust Loose Coupling for Speech Recognition and Natural Understanding.

Descriptive Note : Technical rept.,

Corporate Author : ROCHESTER UNIV NY DEPT OF COMPUTER SCIENCE

Personal Author(s) : Ringger, Eric K.

PDF Url : ADA299910

Report Date : SEP 1995

Pagination or Media Count : 76

Abstract : The focus of this thesis proposal is to improve the ability of a computational system to understand spoken utterances in a dialogue with a human. Available computational methods for word recognition do not perform as well on spontaneous speech as we would hope. Even a state of the art recognizer achieves slightly worse than 70% word accuracy on (nearly) spontaneous speech in a conversation about a specific problem. To address the incrementality of spontaneously spoken utterances, I will develop methods for segmenting a given utterance into 'chunks' representing individual thoughts. Given an utterance of spontaneous speech, a tool for automatic prosodic feature extraction will analyze the output of the error-correcting post-processor and the acoustic waveform to generate prosodic cues. These cues will aid a robust parser using a prosody-wise grammar to identify the incremental phrases in the utterance and to provide a syntactic analysis. These components will augment the TRAINs-95 conversational planning assistant. (AN)

Descriptors :   *SPEECH RECOGNITION, *PATTERN RECOGNITION, MATHEMATICAL MODELS, ALGORITHMS, REAL TIME, ACOUSTIC WAVES, ACCURACY, LEARNING MACHINES, RULE BASED SYSTEMS, ACOUSTIC SIGNALS, KNOWLEDGE BASED SYSTEMS, SPEECH ANALYSIS, MAN COMPUTER INTERFACE, VOCABULARY, NUMERICAL METHODS AND PROCEDURES, DYNAMIC PROGRAMMING, MARKOV PROCESSES, SYNTAX, ERROR CORRECTION CODES, VOICE COMMUNICATIONS, NATURAL LANGUAGE, WORD RECOGNITION, MACHINE TRANSLATION, PHRASE STRUCTURE GRAMMARS, PHONEMES.

Subject Categories : Cybernetics
      Linguistics

Distribution Statement : APPROVED FOR PUBLIC RELEASE