Multi-Resolution Singing Voice Separation

Yih Liang Shen; Ya Ching Lai; Tai Shih Chi

doi:10.1109/O-COCOSDA64382.2024.10800481

Multi-Resolution Singing Voice Separation

Yih Liang Shen, Ya Ching Lai, Tai Shih Chi

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

Abstract

It has been shown that time-domain neural networks achieve higher performance than networks working on the short-time Fourier transform (STFT) domain. The fully-convolutional time-domain audio separation network (Conv-TasNet) is an end-to-end separation model with outstanding performance. However, the fixed convolution kernel length in Conv-TasNet implies that it analyzes signals using the frequency resolution constrained by the kernel length. This paper proposes a multi-frequency-resolution (MF) architecture, which analyzes sig-nals using more frequency resolutions, and compares the MF model with Conv-TasNet on singing voice separation. The results show that the MF architecture improves performance of Conv-TasNet. In addition, we also demonstrate the MF architecture does not provide consistent benefits to the STFT-domain separation model.

Original language	English
Title of host publication	2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings
Editors	Ming-Hsiang Su, Jui-Feng Yeh, Yuan-Fu Liao, Chi-Chun Lee, Yu Taso
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798331506032
DOIs	https://doi.org/10.1109/O-COCOSDA64382.2024.10800481
State	Published - 2024
Event	27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Hsinchu, Taiwan Duration: 17 Oct 2024 → 19 Oct 2024

Publication series

Name	2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings

Conference

Conference	27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024
Country/Territory	Taiwan
City	Hsinchu
Period	17/10/24 → 19/10/24

Keywords

Convolution neural network
end-to-end learning
multi-resolution
singing voice separation

Access to Document

10.1109/O-COCOSDA64382.2024.10800481

Cite this

Shen, Y. L., Lai, Y. C., & Chi, T. S. (2024). Multi-Resolution Singing Voice Separation. In M.-H. Su, J.-F. Yeh, Y.-F. Liao, C.-C. Lee, & Y. Taso (Eds.), 2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings (2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/O-COCOSDA64382.2024.10800481

Shen, Yih Liang ; Lai, Ya Ching ; Chi, Tai Shih. / Multi-Resolution Singing Voice Separation. 2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings. editor / Ming-Hsiang Su ; Jui-Feng Yeh ; Yuan-Fu Liao ; Chi-Chun Lee ; Yu Taso. Institute of Electrical and Electronics Engineers Inc., 2024. (2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings).

@inproceedings{3fd02113d57d442abe49a5b8bec4dc3d,

title = "Multi-Resolution Singing Voice Separation",

abstract = "It has been shown that time-domain neural networks achieve higher performance than networks working on the short-time Fourier transform (STFT) domain. The fully-convolutional time-domain audio separation network (Conv-TasNet) is an end-to-end separation model with outstanding performance. However, the fixed convolution kernel length in Conv-TasNet implies that it analyzes signals using the frequency resolution constrained by the kernel length. This paper proposes a multi-frequency-resolution (MF) architecture, which analyzes sig-nals using more frequency resolutions, and compares the MF model with Conv-TasNet on singing voice separation. The results show that the MF architecture improves performance of Conv-TasNet. In addition, we also demonstrate the MF architecture does not provide consistent benefits to the STFT-domain separation model.",

keywords = "Convolution neural network, end-to-end learning, multi-resolution, singing voice separation",

author = "Shen, {Yih Liang} and Lai, {Ya Ching} and Chi, {Tai Shih}",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 ; Conference date: 17-10-2024 Through 19-10-2024",

year = "2024",

doi = "10.1109/O-COCOSDA64382.2024.10800481",

language = "English",

series = "2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings",

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

editor = "Ming-Hsiang Su and Jui-Feng Yeh and Yuan-Fu Liao and Chi-Chun Lee and Yu Taso",

booktitle = "2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings",

address = "美國",

}

Shen, YL, Lai, YC & Chi, TS 2024, Multi-Resolution Singing Voice Separation. in M-H Su, J-F Yeh, Y-F Liao, C-C Lee & Y Taso (eds), 2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings. 2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024, Hsinchu, Taiwan, 17/10/24. https://doi.org/10.1109/O-COCOSDA64382.2024.10800481

Multi-Resolution Singing Voice Separation. / Shen, Yih Liang; Lai, Ya Ching; Chi, Tai Shih.
2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings. ed. / Ming-Hsiang Su; Jui-Feng Yeh; Yuan-Fu Liao; Chi-Chun Lee; Yu Taso. Institute of Electrical and Electronics Engineers Inc., 2024. (2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings).

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

TY - GEN

T1 - Multi-Resolution Singing Voice Separation

AU - Shen, Yih Liang

AU - Lai, Ya Ching

AU - Chi, Tai Shih

PY - 2024

Y1 - 2024

N2 - It has been shown that time-domain neural networks achieve higher performance than networks working on the short-time Fourier transform (STFT) domain. The fully-convolutional time-domain audio separation network (Conv-TasNet) is an end-to-end separation model with outstanding performance. However, the fixed convolution kernel length in Conv-TasNet implies that it analyzes signals using the frequency resolution constrained by the kernel length. This paper proposes a multi-frequency-resolution (MF) architecture, which analyzes sig-nals using more frequency resolutions, and compares the MF model with Conv-TasNet on singing voice separation. The results show that the MF architecture improves performance of Conv-TasNet. In addition, we also demonstrate the MF architecture does not provide consistent benefits to the STFT-domain separation model.

AB - It has been shown that time-domain neural networks achieve higher performance than networks working on the short-time Fourier transform (STFT) domain. The fully-convolutional time-domain audio separation network (Conv-TasNet) is an end-to-end separation model with outstanding performance. However, the fixed convolution kernel length in Conv-TasNet implies that it analyzes signals using the frequency resolution constrained by the kernel length. This paper proposes a multi-frequency-resolution (MF) architecture, which analyzes sig-nals using more frequency resolutions, and compares the MF model with Conv-TasNet on singing voice separation. The results show that the MF architecture improves performance of Conv-TasNet. In addition, we also demonstrate the MF architecture does not provide consistent benefits to the STFT-domain separation model.

KW - Convolution neural network

KW - end-to-end learning

KW - multi-resolution

KW - singing voice separation

UR - http://www.scopus.com/inward/record.url?scp=85215670231&partnerID=8YFLogxK

U2 - 10.1109/O-COCOSDA64382.2024.10800481

DO - 10.1109/O-COCOSDA64382.2024.10800481

M3 - Conference contribution

AN - SCOPUS:85215670231

T3 - 2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings

BT - 2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings

A2 - Su, Ming-Hsiang

A2 - Yeh, Jui-Feng

A2 - Liao, Yuan-Fu

A2 - Lee, Chi-Chun

A2 - Taso, Yu

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024

Y2 - 17 October 2024 through 19 October 2024

ER -

Shen YL, Lai YC, Chi TS. Multi-Resolution Singing Voice Separation. In Su MH, Yeh JF, Liao YF, Lee CC, Taso Y, editors, 2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2024. (2024 27th Conference on the Oriental COCOSDA International Committee for the Co-Ordination and Standardisation of Speech Databases and Assessment Techniques, O-COCOSDA 2024 - Proceedings). doi: 10.1109/O-COCOSDA64382.2024.10800481

Multi-Resolution Singing Voice Separation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this