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
  • [1] Exploiting Music Source Separation For Singing Voice Detection
    Bonzi, Francesco
    Mancusi, Michele
    Deo, Simone Del
    Melucci, Pierfrancesco
    Tavella, Maria Stella
    Parisi, Loreto
    Rodola, Emanuele
    IEEE International Workshop on Machine Learning for Signal Processing, MLSP, 2023, 2023-September
  • [2] Hybrid binaural singing voice separation
    Kasak, Peter
    Jarina, Roman
    Jakubec, Maros
    Ticha, Dasa
    2023 33RD INTERNATIONAL CONFERENCE RADIOELEKTRONIKA, RADIOELEKTRONIKA, 2023,
  • [3] One microphone singing voice separation using source-adapted models
    Ozerov, A
    Philippe, P
    Gribonval, R
    Bimbot, F
    2005 WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS (WASPAA), 2005, : 90 - 93
  • [4] Study of Indian Classical Music by Singing Voice Analysis and Music Source Separation
    Ghisingh, Seema
    Sharma, Shivam
    Mittal, Vinay Kumar
    2017 2ND INTERNATIONAL CONFERENCE ON TELECOMMUNICATION AND NETWORKS (TEL-NET), 2017, : 133 - 138
  • [5] COMPLEX RATIO MASKING FOR SINGING VOICE SEPARATION
    Zhang, Yixuan
    Liu, Yuzhou
    Wang, DeLiang
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 41 - 45
  • [6] SINGING VOICE SEPARATION: A STUDY ON TRAINING DATA
    Pretet, Laure
    Hennequin, Romain
    Royo-Letelier, Jimena
    Vaglio, Andrea
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 506 - 510
  • [7] Voice and stream: Perceptual and computational modeling of voice separation
    Cambouropoulos, Emilios
    MUSIC PERCEPTION, 2008, 26 (01): : 75 - 94
  • [8] ADVERSARIAL SEMI-SUPERVISED AUDIO SOURCE SEPARATION APPLIED TO SINGING VOICE EXTRACTION
    Stoller, Daniel
    Ewert, Sebastian
    Dixon, Simon
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 2391 - 2395
  • [9] CPPS and Voice-Source Parameters: Objective Analysis of the Singing Voice
    Baker, Calvin P.
    Sundberg, Johan
    Purdy, Suzanne C.
    Rakena, Te Oti
    Leao, Sylvia H. de S.
    JOURNAL OF VOICE, 2024, 38 (03) : 549 - 560
  • [10] Unsupervised Interpretable Representation Learning for Singing Voice Separation
    Mimilakis, Stylianos, I
    Drossos, Konstantinos
    Schuller, Gerald
    28TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2020), 2021, : 1412 - 1416
12345