Spatial diffuseness features for DNN-based speech recognition in noisy and reverberant environments

Schwarz A, Hümmer C, Maas R, Kellermann W (2015)


Publication Language: English

Publication Status: Published

Publication Type: Conference contribution, Conference Contribution

Publication year: 2015

Publisher: Institute of Electrical and Electronics Engineers Inc.

Pages Range: 4380-4384

Article Number: 7178798

Event location: Brisbane AU

ISBN: 978-1-4673-6997-8

DOI: 10.1109/ICASSP.2015.7178798

Abstract

We propose a spatial diffuseness feature for deep neural network (DNN)-based automatic speech recognition to improve recognition accuracy in reverberant and noisy environments. The feature is computed in real-time from multiple microphone signals without requiring knowledge or estimation of the direction of arrival, and represents the relative amount of diffuse noise in each time and frequency bin. It is shown that using the diffuseness feature as an additional input to a DNN-based acoustic model leads to a reduced word error rate for the REVERB challenge corpus, both compared to logmelspec features extracted from noisy signals, and features enhanced by spectral subtraction.

Authors with CRIS profile

How to cite

APA:

Schwarz, A., Hümmer, C., Maas, R., & Kellermann, W. (2015). Spatial diffuseness features for DNN-based speech recognition in noisy and reverberant environments. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (pp. 4380-4384). Brisbane, AU: Institute of Electrical and Electronics Engineers Inc..

MLA:

Schwarz, Andreas, et al. "Spatial diffuseness features for DNN-based speech recognition in noisy and reverberant environments." Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brisbane Institute of Electrical and Electronics Engineers Inc., 2015. 4380-4384.

BibTeX: Download