Title :
An Environment Compensated Maximum Likelihood Training Approach Based on Stochastic Vector Mapping
Author :
Wu, Jian ; Huo, Qiang ; Zhu, Donglai
Author_Institution :
Dept. of Comput. Sci., Hong Kong Univ., China
fDate :
March 18-23, 2005
Keywords :
compensation; hidden Markov models; learning (artificial intelligence); maximum likelihood estimation; parameter estimation; speech recognition; HMM; SVM; SVM function parameter estimation; environment compensated ML training method; environmental variabilities; frame-dependent bias removal; speech recognition robustness; speech recognizer learning behavior; stochastic vector mapping; Automatic speech recognition; Databases; Hidden Markov models; Maximum likelihood estimation; Robustness; Speech recognition; Stochastic processes; Support vector machine classification; Support vector machines; Training data;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 2005. Proceedings. (ICASSP '05). IEEE International Conference on
Print_ISBN :
0-7803-8874-7
DOI :
10.1109/ICASSP.2005.1415142
