Title :
Inference of variable-length acoustic units for continuous speech recognition
Author :
Deligne, Sabine ; Bimbot, Frederic
Author_Institution :
Dept. Signal, Telecom Paris/ENST, France
Abstract :
In the field of speech recognition, the patterns assumed to structure the speech material (phonemes, triphones, words…) are defined a priori according to a linguistic criterion, whereas the recognition criterion is based on an acoustic similarity measure. From this may result a lack of consistency for the recognition units. We explore the possibility of a more data-driven approach, where recognition units are derived according to an acoustic criterion, and then, mapped to variable length sequences of phonemes in an unsupervised way. Continuous speech recognition experiments are reported to evaluate the consistency of those units as opposed to linguistically defined units
Keywords :
acoustic signal processing; grammars; sequences; speech recognition; acoustic criterion; acoustic similarity measure; continuous speech recognition; data driven approach; experiments; linguistic criterion; multigram model; phonemes; recognition criterion; recognition units; speech material; triphones; variable length acoustic units; variable length sequences; words; Acoustic measurements; Distribution functions; Information theory; Maximum likelihood estimation; Pattern recognition; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on
Conference_Location :
Munich
Print_ISBN :
0-8186-7919-0
DOI :
10.1109/ICASSP.1997.598858