Voice separation with an unknown number of multiple speakers

Eliya Nachmani; Yossi Adi; Lior Wolf

Voice separation with an unknown number of multiple speakers

Eliya Nachmani^*, Yossi Adi^*, Lior Wolf^*

^*Corresponding author for this work

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

70 Scopus citations

Abstract

We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.

Original language	English
Title of host publication	37th International Conference on Machine Learning, ICML 2020
Editors	Hal Daume, Aarti Singh
Publisher	International Machine Learning Society (IMLS)
Pages	7121-7132
Number of pages	12
ISBN (Electronic)	9781713821120
State	Published - 2020
Externally published	Yes
Event	37th International Conference on Machine Learning, ICML 2020 - Virtual, Online Duration: 13 Jul 2020 → 18 Jul 2020

Publication series

Name	37th International Conference on Machine Learning, ICML 2020
Volume	PartF168147-10

Conference

Conference	37th International Conference on Machine Learning, ICML 2020
City	Virtual, Online
Period	13/07/20 → 18/07/20

Bibliographical note

Publisher Copyright:
© 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.

Cite this

@inproceedings{206e2ee3d76b47e08156801806baee65,

title = "Voice separation with an unknown number of multiple speakers",

abstract = "We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.",

author = "Eliya Nachmani and Yossi Adi and Lior Wolf",

note = "Publisher Copyright: {\textcopyright} 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.; 37th International Conference on Machine Learning, ICML 2020 ; Conference date: 13-07-2020 Through 18-07-2020",

year = "2020",

language = "אנגלית",

series = "37th International Conference on Machine Learning, ICML 2020",

publisher = "International Machine Learning Society (IMLS)",

pages = "7121--7132",

editor = "Hal Daume and Aarti Singh",

booktitle = "37th International Conference on Machine Learning, ICML 2020",

}

Nachmani, E, Adi, Y & Wolf, L 2020, Voice separation with an unknown number of multiple speakers. in H Daume & A Singh (eds), 37th International Conference on Machine Learning, ICML 2020. 37th International Conference on Machine Learning, ICML 2020, vol. PartF168147-10, International Machine Learning Society (IMLS), pp. 7121-7132, 37th International Conference on Machine Learning, ICML 2020, Virtual, Online, 13/07/20.

Voice separation with an unknown number of multiple speakers. / Nachmani, Eliya; Adi, Yossi; Wolf, Lior.
37th International Conference on Machine Learning, ICML 2020. ed. / Hal Daume; Aarti Singh. International Machine Learning Society (IMLS), 2020. p. 7121-7132 (37th International Conference on Machine Learning, ICML 2020; Vol. PartF168147-10).

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

TY - GEN

T1 - Voice separation with an unknown number of multiple speakers

AU - Nachmani, Eliya

AU - Adi, Yossi

AU - Wolf, Lior

PY - 2020

Y1 - 2020

N2 - We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.

AB - We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.

UR - http://www.scopus.com/inward/record.url?scp=85105253554&partnerID=8YFLogxK

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

AN - SCOPUS:85105253554

T3 - 37th International Conference on Machine Learning, ICML 2020

SP - 7121

EP - 7132

BT - 37th International Conference on Machine Learning, ICML 2020

A2 - Daume, Hal

A2 - Singh, Aarti

PB - International Machine Learning Society (IMLS)

T2 - 37th International Conference on Machine Learning, ICML 2020

Y2 - 13 July 2020 through 18 July 2020

ER -

Voice separation with an unknown number of multiple speakers

Abstract

Publication series

Conference

Bibliographical note

Other files and links

Fingerprint

Cite this