Time-frequency-bin-wise beamformer selection and masking for speech enhancement in underdetermined noisy scenarios

Yamaoka K, Brendel A, Ono N, Makino S, Bürger M, Yamada T, Kellermann W (2018)


Publication Language: English

Publication Type: Conference contribution

Publication year: 2018

Pages Range: 1596-1600

Event location: Rome IT

ISBN: 978-90-827970-1-5

DOI: 10.23919/eusipco.2018.8553299

Abstract

In this paper, we present a speech enhancement method using two microphones for underdetermined situations. A conventional speech enhancement method for underdetermined situations is time-frequency masking, where speech is enhanced by multiplying zero or one to each time-frequency component appropriately. Extending this method, we switch multiple preconstructed beamformers at each time-frequency bin, each of which suppresses a particular interferer. This method can suppress an interferer even when both the target and an interferer are simultaneously active at a given time-frequency bin. As a switching criterion, selection of minimum value of the outputs of the all beamformers at each time-frequency bin is investigated. Additionally, another method using direction of arrival estimation is also investigated. In experiments, we confirmed that the proposed methods were superior to conventional time-frequency masking and fixed beamforming in the performance of speech enhancement.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Yamaoka, K., Brendel, A., Ono, N., Makino, S., Bürger, M., Yamada, T., & Kellermann, W. (2018). Time-frequency-bin-wise beamformer selection and masking for speech enhancement in underdetermined noisy scenarios. In Proceedings of the European Signal Processing Conference (EUSIPCO) (pp. 1596-1600). Rome, IT.

MLA:

Yamaoka, Kouei, et al. "Time-frequency-bin-wise beamformer selection and masking for speech enhancement in underdetermined noisy scenarios." Proceedings of the European Signal Processing Conference (EUSIPCO), Rome 2018. 1596-1600.

BibTeX: Download