ON THE PERCEPTUAL RELEVANCE OF OBJECTIVE SOURCE SEPARATION MEASURES FOR SINGING VOICE SEPARATION

被引：0

作者：

Gupta, Udit ^{[1
]}

Moore, Elliot, II ^{[1
]}

Lerch, Alexander ^{[2
]}

机构：

[1] Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA

[2] Georgia Inst Technol, Ctr Mus Technol, Atlanta, GA 30332 USA

来源：

2015 IEEE WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS (WASPAA) | 2015年

关键词：

Singing Voice Separation; Source Separation; Music Information Retrieval; MUSHRA;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Singing Voice Separation (SVS) is a task which uses audio source separation methods to isolate the vocal component from the background accompaniment for a song mix. This paper discusses the methods of evaluating SVS algorithms, and determines how the current state of the art measures correlate to human perception. A modified ITU-R BS. 1543 MUSHRA test is used to get the human perceptual ratings for the outputs of various SVS algorithms, which are correlated with widely used objective measures for source separation quality. The results show that while the objective measures provide a moderate correlation with perceived intelligibility and isolation, they may not adequately assess the overall perceptual quality.

引用

页数：5

共 50 条

[31] Rethinking Singing Voice Separation With Spectral-Temporal Transformer
Yu, Shuai
Li, Chenxing
Deng, Feng
Wang, Xiaorui
2021 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2021, : 884 - 889
[32] RPCA-DRNN technique for monaural singing voice separation
Lai, Wen-Hsing
Wang, Siou-Lin
EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2022, 2022 (01)
[33] Improving Automatic Singing Skill Evaluation with Timbral Features, Attention, and Singing Voice Separation
Ju, Yaolong
Xu, Chunyang
Guo, Yichen
Li, Jinhu
Lui, Simon
2023 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, ICME, 2023, : 612 - 617
[34] BLIND SOURCE SEPARATION WITH PERCEPTUAL POST PROCESSING
Parikh, Devangi N.
Anderson, David V.
2011 IEEE DIGITAL SIGNAL PROCESSING WORKSHOP AND IEEE SIGNAL PROCESSING EDUCATION WORKSHOP (DSP/SPE), 2011, : 321 - 325
[35] THE DIMENSIONS OF PERCEPTUAL QUALITY OF SOUND SOURCE SEPARATION
Cano, Estefania
Liebetrau, Judith
Fitzgerald, Derry
Brandenburg, Karlheinz
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 601 - 605
[36] EXAMINING THE PERCEPTUAL EFFECT OF ALTERNATIVE OBJECTIVE FUNCTIONS FOR DEEP LEARNING BASED MUSIC SOURCE SEPARATION
Mimilakis, Stylianos Ioannis
Cano, Estefania
FitzGerald, Derry
Drossos, Konstantinos
Schuller, Gerald
2018 CONFERENCE RECORD OF 52ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2018, : 679 - 683
[37] A Novel Singing Voice Separation Method Based on a Learnable Decomposition Technique
Samira Mavaddati
Circuits, Systems, and Signal Processing, 2020, 39 : 3652 - 3681
[38] Choice and adaptation of statistical models for single channel singing voice separation
Ozerov, Alexey
Philippe, Pierrick
Gribonval, Remi
Bimbot, Frederic
TRAITEMENT DU SIGNAL, 2007, 24 (03) : 211 - 224
[39] PROXIMAL DEEP RECURRENT NEURAL NETWORK FOR MONAURAL SINGING VOICE SEPARATION
Yuan, Weitao
Wang, Shengbei
Li, Xiangrui
Unoki, Masashi
Wang, Wenwu
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 286 - 290
[40] Towards Solving the Bottleneck of Pitch-based Singing Voice Separation
Zhu, Bilei
Li, Wei
Li, Linwei
MM'15: PROCEEDINGS OF THE 2015 ACM MULTIMEDIA CONFERENCE, 2015, : 511 - 520

← 1 2 3 4 5 →