DocumentCode :
2799316
Title :
Acoustic model adaptation via Linear Spline Interpolation for robust speech recognition
Author :
Seltzer, Michael L. ; Acero, Alex ; Kalgaonkar, Kaustubh
Author_Institution :
Microsoft Res., Redmond, WA, USA
fYear :
2010
fDate :
14-19 March 2010
Firstpage :
4550
Lastpage :
4553
Abstract :
We recently proposed a new algorithm to perform acoustic model adaptation to noisy environments called Linear Spline Interpolation (LSI). In this method, the nonlinear relationship between clean and noisy speech features is modeled using linear spline regression. Linear spline parameters that minimize the error the between the predicted noisy features and the actual noisy features are learned from training data. A variance associated with each spline segment captures the uncertainty in the assumed model. In this work, we extend the LSI algorithm in two ways. First, the adaptation scheme is extended to compensate for the presence of linear channel distortion. Second, we show how the noise and channel parameters can be updated during decoding in an unsupervised manner within the LSI framework. Using LSI, we obtain an average relative improvement in word error rate of 10.8% over VTS adaptation on the Aurora 2 task with improvements of 15-18% at SNRs between 10 and 15 dB.
Keywords :
feature extraction; interpolation; regression analysis; signal denoising; speech recognition; LSI algorithm; acoustic model adaptation; channel parameter; error minimization; linear channel distortion; linear spline interpolation; noise parameter; noisy environment; noisy speech feature; robust speech recognition; Acoustic noise; Adaptation model; Interpolation; Large scale integration; Robustness; Speech recognition; Spline; Training data; Uncertainty; Working environment noise; model adaptation; robust speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
ISSN :
1520-6149
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2010.5495581
Filename :
5495581
Link To Document :
بازگشت