A simple music/voice separation method based on the extraction of the repeating musical structure

Zafar Rafii; Bryan A Pardo

doi:10.1109/ICASSP.2011.5946380

A simple music/voice separation method based on the extraction of the repeating musical structure

Zafar Rafii^*, Bryan A Pardo

^*Corresponding author for this work

Computer Science

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

49 Scopus citations

Abstract

Repetition is a core principle in music. This is especially true for popular songs, generally marked by a noticeable repeating musical structure, over which the singer performs varying lyrics. On this basis, we propose a simple method for separating music and voice, by extraction of the repeating musical structure. First, the period of the repeating structure is found. Then, the spectrogram is segmented at period boundaries and the segments are averaged to create a repeating segment model. Finally, each time-frequency bin in a segment is compared to the model, and the mixture is partitioned using binary time-frequency masking by labeling bins similar to the model as the repeating background. Evaluation on a dataset of 1,000 song clips showed that this method can improve on the performance of an existing music/voice separation method without requiring particular features or complex frameworks.

Original language	English (US)
Title of host publication	2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
Pages	221-224
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2011.5946380
State	Published - Aug 18 2011
Event	36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Prague, Czech Republic Duration: May 22 2011 → May 27 2011

Other

Other	36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Country	Czech Republic
City	Prague
Period	5/22/11 → 5/27/11

Keywords

Binary Time-Frequency Masking
Music/Voice Separation
Repeating Pattern

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2011.5946380

Fingerprint Dive into the research topics of 'A simple music/voice separation method based on the extraction of the repeating musical structure'. Together they form a unique fingerprint.

Cite this

@inproceedings{281e34e1cc4743d289d76733158e1660,

title = "A simple music/voice separation method based on the extraction of the repeating musical structure",

abstract = "Repetition is a core principle in music. This is especially true for popular songs, generally marked by a noticeable repeating musical structure, over which the singer performs varying lyrics. On this basis, we propose a simple method for separating music and voice, by extraction of the repeating musical structure. First, the period of the repeating structure is found. Then, the spectrogram is segmented at period boundaries and the segments are averaged to create a repeating segment model. Finally, each time-frequency bin in a segment is compared to the model, and the mixture is partitioned using binary time-frequency masking by labeling bins similar to the model as the repeating background. Evaluation on a dataset of 1,000 song clips showed that this method can improve on the performance of an existing music/voice separation method without requiring particular features or complex frameworks.",

keywords = "Binary Time-Frequency Masking, Music/Voice Separation, Repeating Pattern",

author = "Zafar Rafii and Pardo, {Bryan A}",

year = "2011",

month = aug,

day = "18",

doi = "10.1109/ICASSP.2011.5946380",

language = "English (US)",

isbn = "9781457705397",

pages = "221--224",

booktitle = "2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings",

note = "36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 ; Conference date: 22-05-2011 Through 27-05-2011",

}

Rafii, Z & Pardo, BA 2011, A simple music/voice separation method based on the extraction of the repeating musical structure. in 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings., 5946380, pp. 221-224, 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Prague, Czech Republic, 5/22/11. https://doi.org/10.1109/ICASSP.2011.5946380

TY - GEN

T1 - A simple music/voice separation method based on the extraction of the repeating musical structure

AU - Rafii, Zafar

AU - Pardo, Bryan A

PY - 2011/8/18

Y1 - 2011/8/18

N2 - Repetition is a core principle in music. This is especially true for popular songs, generally marked by a noticeable repeating musical structure, over which the singer performs varying lyrics. On this basis, we propose a simple method for separating music and voice, by extraction of the repeating musical structure. First, the period of the repeating structure is found. Then, the spectrogram is segmented at period boundaries and the segments are averaged to create a repeating segment model. Finally, each time-frequency bin in a segment is compared to the model, and the mixture is partitioned using binary time-frequency masking by labeling bins similar to the model as the repeating background. Evaluation on a dataset of 1,000 song clips showed that this method can improve on the performance of an existing music/voice separation method without requiring particular features or complex frameworks.

AB - Repetition is a core principle in music. This is especially true for popular songs, generally marked by a noticeable repeating musical structure, over which the singer performs varying lyrics. On this basis, we propose a simple method for separating music and voice, by extraction of the repeating musical structure. First, the period of the repeating structure is found. Then, the spectrogram is segmented at period boundaries and the segments are averaged to create a repeating segment model. Finally, each time-frequency bin in a segment is compared to the model, and the mixture is partitioned using binary time-frequency masking by labeling bins similar to the model as the repeating background. Evaluation on a dataset of 1,000 song clips showed that this method can improve on the performance of an existing music/voice separation method without requiring particular features or complex frameworks.

KW - Binary Time-Frequency Masking

KW - Music/Voice Separation

KW - Repeating Pattern

UR - http://www.scopus.com/inward/record.url?scp=80051641202&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051641202&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2011.5946380

DO - 10.1109/ICASSP.2011.5946380

M3 - Conference contribution

AN - SCOPUS:80051641202

SN - 9781457705397

SP - 221

EP - 224

BT - 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings

T2 - 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011

Y2 - 22 May 2011 through 27 May 2011

ER -