TY - GEN
T1 - Gaussian mixture models of phonetic boundaries for speech recognition
AU - Omar, M. K.
AU - Hasegawa-Johnson, M.
AU - Levinson, S.
N1 - Publisher Copyright:
© 2001 IEEE.
PY - 2001
Y1 - 2001
N2 - A new approach to represent temporal correlation in an automatic speech recognition system is described. It introduces an acoustic feature set that captures the dynamics of a speech signal at the phoneme boundaries in combination with the traditional acoustic feature set representing the periods that are assumed to be quasi-stationary of speech. This newly introduced feature set represents an observed random vector associated with the state transition in HMM. For the same complexity and number of parameters, this approach improves the phoneme recognition accuracy by 3.5% compared to the context-independent HMM models. Stop consonant recognition accuracy is increased by 40%.
AB - A new approach to represent temporal correlation in an automatic speech recognition system is described. It introduces an acoustic feature set that captures the dynamics of a speech signal at the phoneme boundaries in combination with the traditional acoustic feature set representing the periods that are assumed to be quasi-stationary of speech. This newly introduced feature set represents an observed random vector associated with the state transition in HMM. For the same complexity and number of parameters, this approach improves the phoneme recognition accuracy by 3.5% compared to the context-independent HMM models. Stop consonant recognition accuracy is increased by 40%.
UR - http://www.scopus.com/inward/record.url?scp=77949344977&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77949344977&partnerID=8YFLogxK
U2 - 10.1109/ASRU.2001.1034582
DO - 10.1109/ASRU.2001.1034582
M3 - Conference contribution
AN - SCOPUS:77949344977
T3 - 2001 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Conference Proceedings
SP - 33
EP - 36
BT - 2001 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001 - Conference Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2001
Y2 - 9 December 2001 through 13 December 2001
ER -