Non-stationary environment compensation using sequential EM algorithm for robust speech recognition

Authors:
Haifeng Shen;Jun Guo;Gang Liu;Qunxia Li
Affiliations:
Beijing University of Posts and Telecommunications, Beijing, China;Beijing University of Posts and Telecommunications, Beijing, China;Beijing University of Posts and Telecommunications, Beijing, China;University of Science and Technology Beijing, Beijing, China
Venue:
PKDD'05 Proceedings of the 9th European conference on Principles and Practice of Knowledge Discovery in Databases
Year:
2005

Citing 3
Cited 1

A vector Taylor series approach for environment-independent speech recognition

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 02
Two-domain feature compensation for robust speech recognition

ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
Environment compensation based on maximum a posteriori estimation for improved speech recognition

MICAI'05 Proceedings of the 4th Mexican international conference on Advances in Artificial Intelligence

Environment compensation based on maximum a posteriori estimation for improved speech recognition

MICAI'05 Proceedings of the 4th Mexican international conference on Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper presents a non-stationary environment compensation using sequential EM estimation for tracking the complicated environment. All of the noisy features used in the recognition system are effectively compensated. The speech corruption in the log domain such as the 24 log-filterbank coefficients and the log-energy feature can be modeled as a nonlinear model. For efficient estimating noise parameter using the subsequent sequential Expectation-Maximization (EM) algorithm, the nonlinear environment model is linearized by the truncated first-order vector Taylor series (VTS) approximation. Due to the cepstral features are nearly independence, we train the clean speech using cepstral features and the log-energy feature, and then obtain a diagonal Gaussian mixture model in the log domain by taking inverse discrete cosine transform (IDCT). The experiments are conducted on the large vocabulary continuous speech recognition (LVCSR) system. Results demonstrate that it achieves attractive improvements when compared with CMN (cepstral mean normalization) and the batch-EM based compensation approach.