Title :
Transient part recognition for continuous speech using transition spotting
Author :
Vicard, Dominique
Author_Institution :
OROS SA, Meylan, France
Abstract :
Describes a recognition system for the transient parts of continuous speech. The algorithm uses DTW as distortion measure, and applies it starting at each frame of the unknown signal. The localization of the transient parts in the speech signal is made using a spotting transient part dictionary, as well as with a full diphone one. The output of this system is a lattice of hypothesis among which 65% of the transitions are correctly spotted and recognized. A complete system, using a steady part recognizer has also been designed
Keywords :
speech recognition; DTW; acoustic-phonetic decoding; continuous speech; diphone dictionary; distortion measure; speech recognition system; speech signal; spotting transient part dictionary; steady part recognizer; transient part recognition; transition spotting; Decoding; Dictionaries; Distortion measurement; Dynamic programming; Hidden Markov models; Lattices; Performance evaluation; Speech recognition; Testing; Vectors;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on
Conference_Location :
New York, NY
DOI :
10.1109/ICASSP.1988.196618
