Improved Source Modeling and Predictive Classification for Channel Robust Speech Recognition

V. Ion, R. Haeb-Umbach, in: Interspeech 2006, 2006.

Conference Paper | English
Author
Abstract
The accuracy of distributed speech recognition has been shown to be very sensitive to errors occurring during transmission. One reason for this is that the classifier, usually trained under error free conditions, is unable to cope with the mismatch between an error free and error prone channel. In this paper we present a novel decision rule for classification which is able to account for channel errors. To achieve this, the classical Bayesian speech recognition approach has been reformulated for the server side, where the observation is known only to the extent, as is given by its a posteriori density function. We present a method to estimate the a posteriori density which is based on a Markov model of the source, which captures correlations of both static and dynamic features. A practical implementation is given, accompanied by experimental results for distributed speech recognition over an IP-network.
Publishing Year
Proceedings Title
Interspeech 2006
LibreCat-ID

Cite this

Ion V, Haeb-Umbach R. Improved Source Modeling and Predictive Classification for Channel Robust Speech Recognition. In: Interspeech 2006. ; 2006.
Ion, V., & Haeb-Umbach, R. (2006). Improved Source Modeling and Predictive Classification for Channel Robust Speech Recognition. In Interspeech 2006.
@inproceedings{Ion_Haeb-Umbach_2006, title={Improved Source Modeling and Predictive Classification for Channel Robust Speech Recognition}, booktitle={Interspeech 2006}, author={Ion, Valentin and Haeb-Umbach, Reinhold}, year={2006} }
Ion, Valentin, and Reinhold Haeb-Umbach. “Improved Source Modeling and Predictive Classification for Channel Robust Speech Recognition.” In Interspeech 2006, 2006.
V. Ion and R. Haeb-Umbach, “Improved Source Modeling and Predictive Classification for Channel Robust Speech Recognition,” in Interspeech 2006, 2006.
Ion, Valentin, and Reinhold Haeb-Umbach. “Improved Source Modeling and Predictive Classification for Channel Robust Speech Recognition.” Interspeech 2006, 2006.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]

Link(s) to Main File(s)
Access Level
Restricted Closed Access

Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar