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

Kouei Yamaoka, Andreas Brendel, Nobutaka Ono, Shoji Makino, Michael Buerger, Takeshi Yamada, Walter Kellermann

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

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.

Original languageEnglish
Title of host publication2018 26th European Signal Processing Conference, EUSIPCO 2018
PublisherEuropean Signal Processing Conference, EUSIPCO
Pages1582-1586
Number of pages5
ISBN (Electronic)9789082797015
DOIs
Publication statusPublished - 2018 Nov 29
Externally publishedYes
Event26th European Signal Processing Conference, EUSIPCO 2018 - Rome, Italy
Duration: 2018 Sep 32018 Sep 7

Publication series

NameEuropean Signal Processing Conference
Volume2018-September
ISSN (Print)2219-5491

Conference

Conference26th European Signal Processing Conference, EUSIPCO 2018
Country/TerritoryItaly
CityRome
Period18/9/318/9/7

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Time-frequency-bin-wise beamformer selection and masking for speech enhancement in underdetermined noisy scenarios'. Together they form a unique fingerprint.

Cite this