Beamspace-Domain Multichannel Nonnegative Matrix Factorization for Audio Source Separation

被引：15

作者：

Lee, Seokjin ^{[1
]}

Park, Sang Ha ^{[1
]}

Sung, Koeng-Mo ^{[1
]}

机构：

[1] Seoul Natl Univ, INMC, Seoul 151472, South Korea

来源：

IEEE SIGNAL PROCESSING LETTERS | 2012年 / 19卷 / 01期

关键词：

Acoustic signal processing; blind source separation; multichannel audio; nonnegative matrix factorization (NMF); MIXTURES;

D O I：

10.1109/LSP.2011.2173192

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this letter, we develop a multichannel blind source separation algorithm based on a beamspace transform and the multichannel nonnegative matrix factorization (NMF) method. The conventional multichannel NMF algorithm performs well with multichannel mixing data, but there is still room for enhancement in multichannel real-world recording data. In this letter, we consider a beamspace-time-frequency domain data model for multichannel NMF method, and enhance the conventional method using a beamspace transform. Our decomposition algorithm is applied to 2-channel and 4-channel unsupervised audio source separation, using a dataset from the international Signal Separation Evaluation Campaign 2010 (SiSEC 2010). Our algorithm shows a better performance than the conventional NMF method in an evaluation results.

引用

页码：43 / 46

页数：4

共 50 条

[21] Parallel multichannel blind source separation using a spatial covariance model and nonnegative matrix factorization
A. J. Muñoz-Montoro
J. J. Carabias-Orti
R. Cortina
S. García-Galán
J. Ranilla
[J]. The Journal of Supercomputing, 2021, 77 : 12143 - 12156
[22] Parallel multichannel blind source separation using a spatial covariance model and nonnegative matrix factorization
Munoz-Montoro, A. J.
Carabias-Orti, J. J.
Cortina, R.
Garcia-Galan, S.
Ranilla, J.
[J]. JOURNAL OF SUPERCOMPUTING, 2021, 77 (10): : 12143 - 12156
[23] Temporal annotation-based audio source separation using weighted nonnegative matrix factorization
Duong, Ngoc Q. K.
Ozerov, Alexey
Chevallier, Louis
[J]. 2014 IEEE Fourth International Conference on Consumer Electronics Berlin (ICCE-Berlin), 2014, : 220 - 224
[24] REVERBERANT AUDIO SOURCE SEPARATION USING PARTIALLY PRE-TRAINED NONNEGATIVE MATRIX FACTORIZATION
Fakhry, Mahmoud
Svaizer, Piergiorgio
Omologo, Maurizio
[J]. 2014 14TH INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC), 2014, : 273 - 277
[25] SCORE INFORMED AUDIO SOURCE SEPARATION USING CONSTRAINED NONNEGATIVE MATRIX FACTORIZATION AND SCORE SYNTHESIS
Fritsch, Joachim
Plumbley, Mark D.
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 888 - 891
[26] LINEAR DEMIXED DOMAIN MULTICHANNEL NONNEGATIVE MATRIX FACTORIZATION FOR SPEECH ENHANCEMENT
Taniguchi, Toru
Masuda, Taro
[J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 476 - 480
[27] Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation
Fontaine, Mathieu
Sekiguchi, Kouhei
Nugraha, Aditya Arie
Bando, Yoshiaki
Yoshii, Kazuyoshi
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2022, 30 : 1734 - 1748
[28] Convolutive Transfer Function-Based Multichannel Nonnegative Matrix Factorization for Overdetermined Blind Source Separation
Wang, Taihui
Yang, Feiran
Yang, Jun
[J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2022, 30 : 802 - 815
[29] FAST MULTICHANNEL NONNEGATIVE MATRIX FACTORIZATION WITH CONSTRAINTS ON ACTIVE SOURCE CANDIDATES
Ikeshita, Rintaro
Kawaguchi, Yohei
Nagamatsu, Kenji
[J]. 2018 16TH INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC), 2018, : 520 - 524
[30] TEXT-INFORMED AUDIO SOURCE SEPARATION USING NONNEGATIVE MATRIX PARTIAL CO-FACTORIZATION
Le Magoarou, Luc
Ozerov, Alexey
Duong, Ngoc Q. K.
[J]. 2013 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2013,

← 1 2 3 4 5 →