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
收藏
页数：5
相关论文
共 50 条
  • [41] SINGING VOICE ANALYSIS AND EDITING BASED ON MU TUALLY DEPENDENT F0 ESTIMATION AND SOURCE SEPARATION
    Ikemiya, Yukara
    Yoshii, Kazuyoshi
    Itoyama, Katsutoshi
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 574 - 578
  • [42] A Novel Singing Voice Separation Method Based on a Learnable Decomposition Technique
    Mavaddati, Samira
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2020, 39 (07) : 3652 - 3681
  • [43] BSS EVAL OR PEASS? PREDICTING THE PERCEPTION OF SINGING-VOICE SEPARATION
    Ward, Dominic
    Wierstorf, Hagen
    Mason, Russell D.
    Grais, Emad M.
    Plumbley, Mark D.
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 596 - 600
  • [44] Monaural singing voice separation based on high-resolution network
    Zhang Y.
    Niu Z.
    Niu B.
    Chang Y.
    Niu, Zhixian (niuniurose63@163.com), 1600, Beijing University of Aeronautics and Astronautics (BUAA) (46): : 1555 - 1563
  • [45] PERCEPTUAL CODING-BASED INFORMED SOURCE SEPARATION
    Kirbiz, Serap
    Ozerov, Alexey
    Liutkus, Antoine
    Girin, Laurent
    2014 PROCEEDINGS OF THE 22ND EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2014, : 959 - 963
  • [46] Background-Sound Controllable Voice Source Separation
    Eom, Deokjun
    Nam, Woo Hyun
    Kim, Kyung-Rae
    INTERSPEECH 2023, 2023, : 1698 - 1702
  • [47] Evolving Multi-Resolution Pooling CNN for Monaural Singing Voice Separation
    Yuan, Weitao
    Dong, Bofei
    Wang, Shengbei
    Unoki, Masashi
    Wang, Wenwu
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 29 (29) : 807 - 822
  • [48] Stability of a voice activity detector based on source separation
    Doukas, N
    Stathaki, T
    Naylor, P
    DSP 97: 1997 13TH INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING PROCEEDINGS, VOLS 1 AND 2: SPECIAL SESSIONS, 1997, : 749 - 752
  • [49] OveNet: A Hyper-Range U-Net for Singing Voice Separation
    Wu, Chi-Sheng
    Lee, Shiang
    Soo, Von-Wun
    2019 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM 2019), 2019, : 148 - 151
  • [50] Phoneme Level Lyrics Alignment and Text-Informed Singing Voice Separation
    Schulze-Forster, Kilian
    Doire, Clement S. J.
    Richard, Gael
    Badeau, Roland
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2021, 29 (29) : 2382 - 2395
12345