An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures

Dionyssos Kounades-Bastian; Laurent Girin; Xavier Alameda-Pineda; Sharon Gannot; Radu Horaud

doi:10.1109/ICASSP.2017.7951789

An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures

Dionyssos Kounades-Bastian, Laurent Girin, Xavier Alameda-Pineda, Sharon Gannot, Radu Horaud

Bar-Ilan University - The Alexander Kofkin Faculty of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Scopus citations

Abstract

We present a probabilistic model for joint source separation and diarisation of multichannel convolutive speech mixtures. We build upon the framework of local Gaussian model (LGM) with non-negative matrix factorization (NMF). The diarisation is introduced as a temporal labeling of each source in the mix as active or inactive at the short-term frame level. We devise an EM algorithm in which the source separation process is aided by the diarisation state, since the latter indicates the sources actually present in the mixture. The diarisation state is tracked with a Hidden Markov Model (HMM) with emission probabilities calculated from the estimated source signals. The proposed EM has separation performance comparable with a state-of-the-art LGM NMF method, while outperforming a state-of-the-art speaker diarisation pipeline.

Original language	English
Title of host publication	2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	16-20
Number of pages	5
ISBN (Electronic)	9781509041176
DOIs	https://doi.org/10.1109/ICASSP.2017.7951789
State	Published - 16 Jun 2017
Event	2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States Duration: 5 Mar 2017 → 9 Mar 2017

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
Country/Territory	United States
City	New Orleans
Period	5/03/17 → 9/03/17

Bibliographical note

Publisher Copyright:
© 2017 IEEE.

Funding

This research has received funding from the EU-FP7 STREP project EARS (#609465) and ERC Advanced Grant VHIA (#340113).

Funders	Funder number
EU-FP7
Seventh Framework Programme	609465, 340113
European Commission

Keywords

Audio source separation
local Gaussian model
speaker diarisation

Access to Document

10.1109/ICASSP.2017.7951789

Cite this

Kounades-Bastian, D., Girin, L., Alameda-Pineda, X., Gannot, S., & Horaud, R. (2017). An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 16-20). Article 7951789 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7951789

Kounades-Bastian, Dionyssos ; Girin, Laurent ; Alameda-Pineda, Xavier et al. / An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 16-20 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{7c3bdb08395042929133bed3c5c1371e,

title = "An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures",

abstract = "We present a probabilistic model for joint source separation and diarisation of multichannel convolutive speech mixtures. We build upon the framework of local Gaussian model (LGM) with non-negative matrix factorization (NMF). The diarisation is introduced as a temporal labeling of each source in the mix as active or inactive at the short-term frame level. We devise an EM algorithm in which the source separation process is aided by the diarisation state, since the latter indicates the sources actually present in the mixture. The diarisation state is tracked with a Hidden Markov Model (HMM) with emission probabilities calculated from the estimated source signals. The proposed EM has separation performance comparable with a state-of-the-art LGM NMF method, while outperforming a state-of-the-art speaker diarisation pipeline.",

keywords = "Audio source separation, local Gaussian model, speaker diarisation",

author = "Dionyssos Kounades-Bastian and Laurent Girin and Xavier Alameda-Pineda and Sharon Gannot and Radu Horaud",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 ; Conference date: 05-03-2017 Through 09-03-2017",

year = "2017",

month = jun,

day = "16",

doi = "10.1109/ICASSP.2017.7951789",

language = "אנגלית",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "16--20",

booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",

address = "ארצות הברית",

}

Kounades-Bastian, D, Girin, L, Alameda-Pineda, X, Gannot, S & Horaud, R 2017, An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7951789, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 16-20, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 5/03/17. https://doi.org/10.1109/ICASSP.2017.7951789

An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures. / Kounades-Bastian, Dionyssos; Girin, Laurent; Alameda-Pineda, Xavier et al.
2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 16-20 7951789 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures

AU - Kounades-Bastian, Dionyssos

AU - Girin, Laurent

AU - Alameda-Pineda, Xavier

AU - Gannot, Sharon

AU - Horaud, Radu

PY - 2017/6/16

Y1 - 2017/6/16

N2 - We present a probabilistic model for joint source separation and diarisation of multichannel convolutive speech mixtures. We build upon the framework of local Gaussian model (LGM) with non-negative matrix factorization (NMF). The diarisation is introduced as a temporal labeling of each source in the mix as active or inactive at the short-term frame level. We devise an EM algorithm in which the source separation process is aided by the diarisation state, since the latter indicates the sources actually present in the mixture. The diarisation state is tracked with a Hidden Markov Model (HMM) with emission probabilities calculated from the estimated source signals. The proposed EM has separation performance comparable with a state-of-the-art LGM NMF method, while outperforming a state-of-the-art speaker diarisation pipeline.

AB - We present a probabilistic model for joint source separation and diarisation of multichannel convolutive speech mixtures. We build upon the framework of local Gaussian model (LGM) with non-negative matrix factorization (NMF). The diarisation is introduced as a temporal labeling of each source in the mix as active or inactive at the short-term frame level. We devise an EM algorithm in which the source separation process is aided by the diarisation state, since the latter indicates the sources actually present in the mixture. The diarisation state is tracked with a Hidden Markov Model (HMM) with emission probabilities calculated from the estimated source signals. The proposed EM has separation performance comparable with a state-of-the-art LGM NMF method, while outperforming a state-of-the-art speaker diarisation pipeline.

KW - Audio source separation

KW - local Gaussian model

KW - speaker diarisation

UR - http://www.scopus.com/inward/record.url?scp=85023750194&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7951789

DO - 10.1109/ICASSP.2017.7951789

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85023750194

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 16

EP - 20

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017

Y2 - 5 March 2017 through 9 March 2017

ER -

Kounades-Bastian D, Girin L, Alameda-Pineda X, Gannot S, Horaud R. An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 16-20. 7951789. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2017.7951789

An em algorithm for joint source separation and diarisation of multichannel convolutive speech mixtures

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this