VOCAL ACTIVITY INFORMED SINGING VOICE SEPARATION WITH THE IKALA DATASET

被引：0

作者：

Chan, Tak-Shing ^{[1
]}

Yeh, Tzu-Chun ^{[2
]}

Fan, Zhe-Cheng ^{[2
]}

Chen, Hung-Wei ^{[3
]}

Sui, Li ^{[1
]}

Yang, Yi-Hsuan ^{[1
]}

Jang, Roger ^{[2
]}

机构：

[1] Acad Sinica, Res Ctr Informat Technol Innovat, Taipei, Taiwan

[2] Natl Taiwan Univ, Dept Comp Sci & Informat Engn, Taipei, Taiwan

[3] iKala Interact Media Inc, Taipei, Taiwan

来源：

2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP) | 2015年

关键词：

Low-rank and sparse decomposition; singing voice separation; informed source separation; RECORDINGS; MUSIC; SOUND;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

A new algorithm is proposed for robust principal component analysis with predefined sparsity patterns. The algorithm is then applied to separate the singing voice from the instrumental accompaniment using vocal activity information. To evaluate its performance, we construct a new publicly available iKala dataset that features longer durations and higher quality than the existing MIR-IK dataset for singing voice separation. Part of it will be used in the MIREX Singing Voice Separation task. Experimental results on both the MIR-IK dataset and the new iKala dataset confirmed that the more informed the algorithm is, the better the separation results are.

引用

页码：718 / 722

页数：5

共 50 条

[41] 'SINGING, PHYSICAL NATURE OF VOCAL ORGAN, A GUIDE TO UNLOCKING OF SINGING VOICE' - HUSLER,F, RODDMARLING,Y
HOWARD, VA
INTERFACE-JOURNAL OF NEW MUSIC RESEARCH, 1977, 6 (3-4): : 151 - 163
[42] Contemporary Commercial Music Singing Students-Voice Quality and Vocal Function at the Beginning of Singing Training
Sielska-Badurek, Ewelina M.
Sobol, Maria
Olszowska, Katarzyna
Niemczyk, Kazimierz
JOURNAL OF VOICE, 2018, 32 (06) : 668 - 672
[43] Karalk: a karaoke dataset for cover song identification and singing voice analysis
Bayle, Yann
Marsik, Ladislav
Rusek, Martin
Robine, Matthias
Hanna, Pierre
Slaninova, Katerina
Martinovic, Jan
Pokorny, Jaroslav
2017 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM), 2017, : 177 - 184
[44] Singing voice separation with pre-learned dictionary and reconstructed voice spectrogram
Chenghong Yang
Hongjuan Zhang
Neural Computing and Applications, 2020, 32 : 3311 - 3322
[45] Singing voice separation with pre-learned dictionary and reconstructed voice spectrogram
Yang, Chenghong
Zhang, Hongjuan
NEURAL COMPUTING & APPLICATIONS, 2020, 32 (08): : 3311 - 3322
[46] The singing voice is special: Persistence of superior memory for vocal melodies despite vocal-motor distractions
Weiss, Michael W.
Bissonnette, Anne-Marie
Peretz, Isabelle
COGNITION, 2021, 213
[47] 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
[48] VOICE SOURCE EFFECTS OF DIAPHRAGMATIC ACTIVITY IN SINGING
SUNDBERG, J
LEANDERSON, R
VONEULER, C
JOURNAL OF PHONETICS, 1986, 14 (3-4) : 351 - 357
[49] Perceptions of Voice Teachers Regarding Students' Vocal Behaviors During Singing and Speaking
Beeman, Shellie A.
JOURNAL OF VOICE, 2017, 31 (01) : 111.e19 - 111.e28
[50] Navigating Vocal Challenges: Singing Difficulties in a Carnatic Singer with Clinically Normal Voice
Krishna, Yeshoda
Raveendran, Revathi
INDIAN JOURNAL OF OTOLARYNGOLOGY AND HEAD & NECK SURGERY, 2024, 76 (04) : 3596 - 3603

← 1 2 3 4 5 →