Discriminative Nonnegative Matrix Factorization Using Cross-Reconstruction Error for Source Separation

被引：0

作者：

Kwon, Kisoo ^{[1
,2
]}

Shin, Jong Won ^{[3
]}

Kim, Hyung Yong ^{[1
,2
]}

Kim, Nam Soo ^{[1
,2
]}

机构：

[1] Seoul Natl Univ, Dept Elect & Comp Engn, Seoul, South Korea

[2] Seoul Natl Univ, INMC, Seoul, South Korea

[3] Gwangju Inst Sci & Technol, Sch Informat & Commun, Gwangju, South Korea

来源：

16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5 | 2015年

关键词：

non-negative matrix factorization; discriminative basis; cross-reconstruction error;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

Non-negative matrix factorization (NMF) is a dimensionality reduction method that usually leads to a part-based representation, and it is shown to be effective for source separation. However, the performance of the source separation degrades when one signal can be described with the bases for the other source signals. In this paper, we propose a discriminative NMF (DNMF) algorithm which exploits the reconstruction error for the other signals as well as the target signal based on target bases. The objective function to train the basis matrix is constructed to reward high reconstruction error for the other source signals in addition to low reconstruction error for the signal from the corresponding source. Experiments showed that the proposed method outperformed the standard NMF by about 0.26 in perceptual evaluation of speech quality score and 1.95 dB in signal-to-distortion ratio when it is applied to speech enhancement at input SNR of 0 dB.

引用

页码：1513 / 1516

页数：4

共 50 条

[31] β-Divergence Two-Dimensional Sparse Nonnegative Matrix Factorization for Audio Source Separation
Darsono, A. M.
Haron, N. Z.
Jaafar, A. S.
Ahmad, M. I.
2013 IEEE CONFERENCE ON WIRELESS SENSOR (ICWISE), 2013, : 119 - 123
[32] Hybrid Projective Nonnegative Matrix Factorization With Drum Dictionaries for Harmonic/Percussive Source Separation
Laroche, Clement
Kowalski, Matthieu
Papadopoulos, Helene
Richard, Gael
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2018, 26 (09) : 1499 - 1511
[33] Supervised Audio Source Separation Based on Nonnegative Matrix Factorization with Cosine Similarity Penalty
Iwase, Yuta
Kitamura, Daichi
IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2022, E105A (06) : 906 - 913
[34] Determined Blind Source Separation Unifying Independent Vector Analysis and Nonnegative Matrix Factorization
Kitamura, Daichi
Ono, Nobutaka
Sawada, Hiroshi
Kameoka, Hirokazu
Saruwatari, Hiroshi
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2016, 24 (09) : 1626 - 1641
[35] Monaural sound source separation by nonnegative matrix factorization with tempora continuity and sparseness criteria
Virtanen, Tuomas
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2007, 15 (03): : 1066 - 1074
[36] Graph-based discriminative nonnegative matrix factorization with label information
Li, Huirong
Zhang, Jiangshe
Shi, Guang
Liu, Junmin
NEUROCOMPUTING, 2017, 266 : 91 - 100
[37] Nonnegative Matrix Factorization with Hypergraph Based on Discriminative Constraint and Nonsymmetric Reformulation
Pan, Sigan
Yang, Lei
2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 7441 - 7446
[38] Transductive Convolutive Nonnegative Matrix Factorization for Speech Separation
Mai, Yaodan
Lan, Long
Guan, Naiyang
Zhang, Xiang
Luo, Zhigang
PROCEEDINGS OF 2015 4TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT 2015), 2015, : 1400 - 1404
[39] Orthogonal Nonnegative Matrix Factorization for Blind Image Separation
Mirzal, Andri
ADVANCES IN VISUAL INFORMATICS, 2013, 8237 : 25 - 35
[40] Deep Transductive Nonnegative Matrix Factorization for Speech Separation
Liu, Yalin
Guan, Naiyang
Liu, Jie
2017 16TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2017, : 249 - 254

← 1 2 3 4 5 →