A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition

A. Krueger, R. Haeb-Umbach, in: R. Haeb-Umbach, D. Kolossa (Eds.), Robust Speech Recognition of Uncertain or Missing Data, Springer, 2011.

Download
No fulltext has been uploaded.
Book Chapter | English
Author
;
Book Editor
;
Abstract
Employing automatic speech recognition systems in hands-free communication applications is accompanied by perfomance degradation due to background noise and, in particular, due to reverberation. These two kinds of distortion alter the shape of the feature vector trajectory extracted from the microphone signal and consequently lead to a discrepancy between training and testing conditions for the recognizer. In this chapter we present a feature enhancement approach aiming at the joint compensation of noise and reverberation to improve the performance by restoring the training conditions. For the enhancement we concentrate on the logarithmic mel power spectral coefficients as features, which are computed at an intermediate stage to obtain the widely used mel frequency cepstral coefficients. The proposed technique is based on a Bayesian framework, to attempt to infer the posterior distribution of the clean features given the observation of all past corrupted features. It exploits information from a priori models describing the dynamics of clean speech and noise-only feature vector trajectories as well as from an observation model relating the reverberant noisy to the clean features. The observation model relies on a simplified stochastic model of the room impulse response (RIR) between the speaker and the microphone, having only two parameters, namely RIR energy and reverberation time, which can be estimated from the captured microphone signal. The performance of the proposed enhancement technique is finally experimentally studied by means of recognition accuracy obtained for a connected digits recognition task under different noise and reverberation conditions using the Aurora~5 database.
Publishing Year
Book Title
Robust Speech Recognition of Uncertain or Missing Data
LibreCat-ID

Cite this

Krueger A, Haeb-Umbach R. A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition. In: Haeb-Umbach R, Kolossa D, eds. Robust Speech Recognition of Uncertain or Missing Data. Springer; 2011.
Krueger, A., & Haeb-Umbach, R. (2011). A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition. In R. Haeb-Umbach & D. Kolossa (Eds.), Robust Speech Recognition of Uncertain or Missing Data. Springer.
@inbook{Krueger_Haeb-Umbach_2011, title={A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition}, booktitle={Robust Speech Recognition of Uncertain or Missing Data}, publisher={Springer}, author={Krueger, Alexander and Haeb-Umbach, Reinhold}, editor={Haeb-Umbach, Reinhold and Kolossa, DorotheaEditors}, year={2011} }
Krueger, Alexander, and Reinhold Haeb-Umbach. “A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition.” In Robust Speech Recognition of Uncertain or Missing Data, edited by Reinhold Haeb-Umbach and Dorothea Kolossa. Springer, 2011.
A. Krueger and R. Haeb-Umbach, “A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition,” in Robust Speech Recognition of Uncertain or Missing Data, R. Haeb-Umbach and D. Kolossa, Eds. Springer, 2011.
Krueger, Alexander, and Reinhold Haeb-Umbach. “A Model-Based Approach to Joint Compensation of Noise and Reverberation for Speech Recognition.” Robust Speech Recognition of Uncertain or Missing Data, edited by Reinhold Haeb-Umbach and Dorothea Kolossa, Springer, 2011.

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar