Joint optimization of LCMV beamforming and acoustic echo cancellation for automatic speech recognition

Herbordt W, Nakamura S, Kellermann W (2005)


Publication Language: English

Publication Status: Published

Publication Type: Conference contribution, Conference Contribution

Publication year: 2005

Publisher: Institute of Electrical and Electronics Engineers Inc.

Article Number: 1415650

Event location: Philadelphia, PA US

ISBN: 9780780388741

DOI: 10.1109/ICASSP.2005.1415650

Abstract

For full-duplex hands-free acoustic human/machine interfaces, often a combination of acoustic echo cancellation and speech enhancement in order to suppress acoustic echoes, local interference, and noise is required. In order to optimally exploit positive synergies between acoustic echo cancellation and speech enhancement, we presented in an earlier work a combined least-squares (LS) optimization criterion for the integration of acoustic echo cancellation and adaptive linearly-constrained minimum variance (LCMV) beamforming [1]. In this contribution, we illustrate the efficiency of the proposed solution in situations with high levels of background noise and with time-varying echo paths and frequent double-talk by speech recognition experiments. ©2005 IEEE.

Authors with CRIS profile

How to cite

APA:

Herbordt, W., Nakamura, S., & Kellermann, W. (2005). Joint optimization of LCMV beamforming and acoustic echo cancellation for automatic speech recognition. In Proceedings of the 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05. Philadelphia, PA, US: Institute of Electrical and Electronics Engineers Inc..

MLA:

Herbordt, Wolfgang, S. Nakamura, and Walter Kellermann. "Joint optimization of LCMV beamforming and acoustic echo cancellation for automatic speech recognition." Proceedings of the 2005 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '05, Philadelphia, PA Institute of Electrical and Electronics Engineers Inc., 2005.

BibTeX: Download