Hands-free speech recognition using a reverberation model in the feature domain

Sehr A, Zeller M, Kellermann W (2006)

Publication Language: English

Publication Status: Published

Publication Type: Conference contribution, Conference Contribution

Publication year: 2006

Publisher: IEEE

Event location: Florence IT

URI: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84862601866∨igin=inward

Abstract

A novel approach for robust hands-free speech recognition in highly reverberant environments is proposed. Unlike conventional HMMbased concepts, it implicitly accounts for the statistical dependence of successive feature vectors due to the reverberation. This property is attained by a combined acoustic model consisting of a conventional HMM, modeling the clean speech, and a reverberation model. Since the HMM is independent of the acoustic environment, it needs to be trained only once using the usual Baum-Welch reestimation procedure. The training of the reverberation model is based on a set of room impulse responses for the corresponding acoustic environment and involves only a negligible computational effort. Thus, the recognizer can be adapted to new environments with moderate effort. In a simulation of an isolated digit recognition task in a highly reverberant room, the proposed method achieves a 60% reduction of the word error rate compared to a conventional HMM trained on reverberant speech, at the cost of an increased decoding complexity.

Authors with CRIS profile

Armin Sehr Professur für Signalverarbeitung Marcus Zeller Lehrstuhl für Multimediakommunikation und Signalverarbeitung Walter Kellermann Professur für Signalverarbeitung

How to cite

APA:

Sehr, A., Zeller, M., & Kellermann, W. (2006). Hands-free speech recognition using a reverberation model in the feature domain. In Proceedings of the 14th European Signal Processing Conference, EUSIPCO 2006. Florence, IT: IEEE.

MLA:

Sehr, Armin, Marcus Zeller, and Walter Kellermann. "Hands-free speech recognition using a reverberation model in the feature domain." Proceedings of the 14th European Signal Processing Conference, EUSIPCO 2006, Florence IEEE, 2006.

BibTeX: Download