Maximum likelihood estimation of a reverberation model for robust distant-talking speech recognition

Sehr A, Zheng Y, Nöth E, Kellermann W (2007)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2007

Original Authors: Sehr Armin, Zeng Yuanhang, Nöth Elmar, Kellermann Walter

Pages Range: 1299-1303

Conference Proceedings Title: Proc. European Signal Processing Conference

Event location: Poznan PL

ISBN: 9788392134022

URI: http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2007/Sehr07-MLE.pdf

Abstract

We propose a novel approach for estimating a reverberation model for a robust recognizer according to [1], which is designed to allow distant-talking automatic speech recognition (ASR) in reverberant environments. Based on a few calibration utterances with known transcriptions recorded in the target environment, a maximum likelihood estimator is used to find the means and variances of the reverberation model. In contrast to [1] and to HMM training on artificially reverberated training data (e. g. [2]), measurements of room impulse responses become unnecessary, and the effort for training is greatly reduced. Simulations of a connected digit recognition task show that, in highly reverberant environments, the reverberation models estimated by the proposed approach achieve significantly higher recognition rates than HMMs trained on reverberant data. © 2007 EURASIP.

Authors with CRIS profile

How to cite

APA:

Sehr, A., Zheng, Y., Nöth, E., & Kellermann, W. (2007). Maximum likelihood estimation of a reverberation model for robust distant-talking speech recognition. In Proc. European Signal Processing Conference (pp. 1299-1303). Poznan, PL.

MLA:

Sehr, Armin, et al. "Maximum likelihood estimation of a reverberation model for robust distant-talking speech recognition." Proceedings of the 15th European Signal Processing Conference, EUSIPCO 2007, Poznan 2007. 1299-1303.

BibTeX: Download