Singing voice detection with deep recurrent neural networks

Simon Leglaive; Romain Hennequin; Roland Badeau

doi:10.1109/ICASSP.2015.7177944

Singing voice detection with deep recurrent neural networks

Simon Leglaive, Romain Hennequin, Roland Badeau

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

Abstract

In this paper, we propose a new method for singing voice detection based on a Bidirectional Long Short-Term Memory (BLSTM) Recurrent Neural Network (RNN). This classifier is able to take a past and future temporal context into account to decide on the presence/absence of singing voice, thus using the inherent sequential aspect of a short-term feature extraction in a piece of music. The BLSTM-RNN contains several hidden layers, so it is able to extract a simple representation fitted to our task from low-level features. The results we obtain significantly outperform state-of-the-art methods on a common database.

Original language	English
Title of host publication	2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	121-125
Number of pages	5
ISBN (Electronic)	9781467369978
DOIs	https://doi.org/10.1109/ICASSP.2015.7177944
Publication status	Published - 4 Aug 2015
Event	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia Duration: 19 Apr 2014 → 24 Apr 2014

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2015-August
ISSN (Print)	1520-6149

Conference

Conference	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Country/Territory	Australia
City	Brisbane
Period	19/04/14 → 24/04/14

Keywords

Deep Learning
Long Short-Term Memory
Recurrent Neural Networks
Singing Voice Detection

Access to Document

10.1109/ICASSP.2015.7177944

Cite this

Leglaive, S., Hennequin, R., & Badeau, R. (2015). Singing voice detection with deep recurrent neural networks. In 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings (pp. 121-125). Article 7177944 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2015-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2015.7177944

Leglaive, Simon ; Hennequin, Romain ; Badeau, Roland. / Singing voice detection with deep recurrent neural networks. 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 121-125 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{86251389e5fc451f8a792ef5965d6fcc,

title = "Singing voice detection with deep recurrent neural networks",

abstract = "In this paper, we propose a new method for singing voice detection based on a Bidirectional Long Short-Term Memory (BLSTM) Recurrent Neural Network (RNN). This classifier is able to take a past and future temporal context into account to decide on the presence/absence of singing voice, thus using the inherent sequential aspect of a short-term feature extraction in a piece of music. The BLSTM-RNN contains several hidden layers, so it is able to extract a simple representation fitted to our task from low-level features. The results we obtain significantly outperform state-of-the-art methods on a common database.",

keywords = "Deep Learning, Long Short-Term Memory, Recurrent Neural Networks, Singing Voice Detection",

author = "Simon Leglaive and Romain Hennequin and Roland Badeau",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 ; Conference date: 19-04-2014 Through 24-04-2014",

year = "2015",

month = aug,

day = "4",

doi = "10.1109/ICASSP.2015.7177944",

language = "English",

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

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

pages = "121--125",

booktitle = "2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings",

}

Leglaive, S, Hennequin, R & Badeau, R 2015, Singing voice detection with deep recurrent neural networks. in 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings., 7177944, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2015-August, Institute of Electrical and Electronics Engineers Inc., pp. 121-125, 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015, Brisbane, Australia, 19/04/14. https://doi.org/10.1109/ICASSP.2015.7177944

Singing voice detection with deep recurrent neural networks. / Leglaive, Simon; Hennequin, Romain; Badeau, Roland.
2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 121-125 7177944 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2015-August).

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

TY - GEN

T1 - Singing voice detection with deep recurrent neural networks

AU - Leglaive, Simon

AU - Hennequin, Romain

AU - Badeau, Roland

PY - 2015/8/4

Y1 - 2015/8/4

N2 - In this paper, we propose a new method for singing voice detection based on a Bidirectional Long Short-Term Memory (BLSTM) Recurrent Neural Network (RNN). This classifier is able to take a past and future temporal context into account to decide on the presence/absence of singing voice, thus using the inherent sequential aspect of a short-term feature extraction in a piece of music. The BLSTM-RNN contains several hidden layers, so it is able to extract a simple representation fitted to our task from low-level features. The results we obtain significantly outperform state-of-the-art methods on a common database.

AB - In this paper, we propose a new method for singing voice detection based on a Bidirectional Long Short-Term Memory (BLSTM) Recurrent Neural Network (RNN). This classifier is able to take a past and future temporal context into account to decide on the presence/absence of singing voice, thus using the inherent sequential aspect of a short-term feature extraction in a piece of music. The BLSTM-RNN contains several hidden layers, so it is able to extract a simple representation fitted to our task from low-level features. The results we obtain significantly outperform state-of-the-art methods on a common database.

KW - Deep Learning

KW - Long Short-Term Memory

KW - Recurrent Neural Networks

KW - Singing Voice Detection

U2 - 10.1109/ICASSP.2015.7177944

DO - 10.1109/ICASSP.2015.7177944

M3 - Conference contribution

AN - SCOPUS:84946078198

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

SP - 121

EP - 125

BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

Y2 - 19 April 2014 through 24 April 2014

ER -

Leglaive S, Hennequin R, Badeau R. Singing voice detection with deep recurrent neural networks. In 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 121-125. 7177944. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2015.7177944

Singing voice detection with deep recurrent neural networks

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this