A Two-Channel Acoustic Front-End for Robust Automatic Speech Recognition in Noisy and Reverberant Environments

Maas R, Schwarz A, Zheng Y, Reindl K, Meier S, Sehr A, Kellermann W (2011)


Publication Language: English

Publication Type: Conference contribution

Publication year: 2011

City/Town: Florence, Italy

Pages Range: 41-46

Conference Proceedings Title: International Workshop on Machine Listening in Multisource Environments (CHiME)

Event location: Florence IT

Abstract

An acoustic front-end for robust automatic speech recognition in noisy and reverberant environments is pro-posed in this contribution. It comprises a blind source separation-based signal extraction scheme and only re-quires two microphone signals. The proposed front-end and its integration into the recognition system is analyzed and evaluated in noisy living room-like environments ac-cording to the PASCAL CHiME challenge. The results show that the introduced system significantly improves the recognition performance compared to the challenge baseline.

Authors with CRIS profile

How to cite

APA:

Maas, R., Schwarz, A., Zheng, Y., Reindl, K., Meier, S., Sehr, A., & Kellermann, W. (2011). A Two-Channel Acoustic Front-End for Robust Automatic Speech Recognition in Noisy and Reverberant Environments. In International Workshop on Machine Listening in Multisource Environments (CHiME) (pp. 41-46). Florence, IT: Florence, Italy.

MLA:

Maas, Roland, et al. "A Two-Channel Acoustic Front-End for Robust Automatic Speech Recognition in Noisy and Reverberant Environments." Proceedings of the International Workshop on Machine Listening in Multisource Environments (CHiME), Florence Florence, Italy, 2011. 41-46.

BibTeX: Download