TY - GEN
T1 - Incremental adaptation based on a macroscopic time evolution system
AU - Watanabe, Shinji
AU - Nakamura, Atsushi
PY - 2007/8/6
Y1 - 2007/8/6
N2 - In this paper, we propose a new incremental model adaptation approach based on posterior distributions of model parameters. We consider a propagation mechanism of the posterior distributions whereby that the process of posterior refinement is modeled analytically. Then, we derive an incremental estimation algorithm based on a time evolution system, which explicitly includes a discrete stochastic process unlike the conventional Bayesian approaches. This algorithm is viewed as a general solution of the Kalman filter algorithm, where posterior distributions make a transition after every input of an utterance set, and where the evolutions of posterior distributions are represented on a macroscopic time scale.
AB - In this paper, we propose a new incremental model adaptation approach based on posterior distributions of model parameters. We consider a propagation mechanism of the posterior distributions whereby that the process of posterior refinement is modeled analytically. Then, we derive an incremental estimation algorithm based on a time evolution system, which explicitly includes a discrete stochastic process unlike the conventional Bayesian approaches. This algorithm is viewed as a general solution of the Kalman filter algorithm, where posterior distributions make a transition after every input of an utterance set, and where the evolutions of posterior distributions are represented on a macroscopic time scale.
KW - Acoustic model
KW - Discrete stochastic process
KW - Incremental adaptation
KW - Macroscopic time evolution
KW - Speech recognition
UR - http://www.scopus.com/inward/record.url?scp=34547552788&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=34547552788&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2007.367026
DO - 10.1109/ICASSP.2007.367026
M3 - Conference contribution
AN - SCOPUS:34547552788
SN - 1424407281
SN - 9781424407286
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - IV769-IV772
BT - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
T2 - 2007 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '07
Y2 - 15 April 2007 through 20 April 2007
ER -