By Topic

Combining feature compensation and weighted Viterbi decoding for noise robust speech recognition with limited adaptation data

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Cui, Xiaodong ; Dept. of Electr. Eng., Univ. of California, Los Angeles, CA, USA ; Alwan, Abeer

Acoustic models trained with clean speech signals suffer in the presence of background noise. In some situations, only a limited amount of noisy data of the new environment is available based on which the clean models could be adapted. A feature compensation approach employing polynomial regression of the signal-to-noise ratio (SNR) is proposed in this paper. While clean acoustic models remain unchanged, a bias which is a polynomial function of utterance SNR is estimated and removed from the noisy feature. Depending on the amount of noisy data available, the algorithm could be flexibly carried out at different levels of granularity. Based on the Euclidean distance, the similarity between the residual distribution and the clean models are estimated and used as the confidence factor in a back-end weighted Viterbi decoding (WVD) algorithm. With limited amounts of noisy data, the feature compensation algorithm outperforms maximum likelihood linear regression (MLLR) for the Aurora2 database. Weighted Viterbi decoding further improves recognition accuracy.

Published in:

Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on  (Volume:1 )

Date of Conference:

17-21 May 2004