Cancellation of Local Competing Speaker with Near-field Localization for Distributed Ad-Hoc Sensor Network

Pablo Perez Zarazaga, Mariem Bouafif, Tom Bäckström, Zied Lachiri

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

171 Downloads (Pure)

Abstract

In scenarios such as remote work, open offices and call centers, multiple people may simultaneously have independent spoken interactions with their devices in the same room. The speech of competing speakers will however be picked up by all microphones, both reducing the quality of audio and exposing speakers to breaches in privacy. We propose a cooperative cross-talk cancellation solution breaking the single active speaker assumption employed by most telecommunication systems. The proposed method applies source separation on the microphone signals of independent devices, to extract the dominant speaker in each device. It is realized using a localization estimator based on a deep neural network, followed by a time-frequency mask to separate the target speech from the interfering one at each time-frequency unit referring to its orientation. By experimental evaluation, we confirm that the proposed method effectively reduces crosstalk and exceeds the baseline expectation maximization method by 10 dB in terms of interference rejection. This performance makes the proposed method a viable solution for cross-talk cancellation in near-field conditions, thus protecting the privacy of external speakers in the same acoustic space.

Original languageEnglish
Title of host publication22nd Annual Conference of the International Speech Communication Association, INTERSPEECH 2021
PublisherInternational Speech Communication Association (ISCA)
Pages1176-1180
Number of pages5
ISBN (Electronic)9781713836902
DOIs
Publication statusPublished - 31 Aug 2021
MoE publication typeA4 Conference publication
EventInterspeech - Brno, Czech Republic
Duration: 30 Aug 20213 Sept 2021
Conference number: 22

Publication series

NameAnnual Conference of the International Speech Communication Association
ISSN (Print)1990-9772
ISSN (Electronic)2308-457X

Conference

ConferenceInterspeech
Abbreviated titleINTERSPEECH
Country/TerritoryCzech Republic
CityBrno
Period30/08/202103/09/2021

Fingerprint

Dive into the research topics of 'Cancellation of Local Competing Speaker with Near-field Localization for Distributed Ad-Hoc Sensor Network'. Together they form a unique fingerprint.

Cite this