A binaural scene analyzer for joint localization and recognition of speakers in the presence of interfering noise sources and reverberation

T. May, S.L.J.D.E. Par, van de, A.G. Kohlrausch

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

51 Citaten (Scopus)
2 Downloads (Pure)

Samenvatting

In this study, we present a binaural scene analyzer that is able to simultaneously localize, detect and identify a known number of target speakers in the presence of spatially positioned noise sources and reverberation. In contrast to many other binaural cocktail party processors, the proposed system does not require a priori knowledge about the azimuth position of the target speakers. The proposed system consists of three main building blocks: binaural localization, speech source detection, and automatic speaker identification. First, a binaural front-end is used to robustly localize relevant sound source activity. Second, a speech detection module based on missing data classification is employed to determine whether detected sound source activity corresponds to a speaker or to an interfering noise source using a binary mask that is based on spatial evidence supplied by the binaural front-end. Third, a second missing data classifier is used to recognize the speaker identities of all detected speech sources. The proposed system is systematically evaluated in simulated adverse acoustic scenarios. Compared to state-of-the art MFCC recognizers, the proposed model achieves significant speaker recognition accuracy improvements.
Originele taal-2Engels
Pagina's (van-tot)2016-2030
Aantal pagina's15
TijdschriftIEEE Transactions on Audio, Speech, and Language Processing
Volume20
Nummer van het tijdschrift7
DOI's
StatusGepubliceerd - 2012

Vingerafdruk Duik in de onderzoeksthema's van 'A binaural scene analyzer for joint localization and recognition of speakers in the presence of interfering noise sources and reverberation'. Samen vormen ze een unieke vingerafdruk.

Citeer dit