AMPLITUDE-BASED SPEECH ENHANCEMENT WITH NONNEGATIVE MATRIX FACTORIZATION FOR ASYNCHRONOUS DISTRIBUTED RECORDING

被引：0

作者：

Chiba, Hironobu ^{[1
]}

Ono, Nobutaka ^{[2
,3
]}

Miyabe, Shigeki ^{[1
]}

Takahashi, Yu ^{[4
]}

Yamada, Takeshi ^{[1
]}

Makino, Shoji ^{[1
]}

机构：

[1] Univ Tsukuba, Tsukuba, Ibaraki 3058577, Japan

[2] Res Org Informat & Syst, Natl Inst Informat, Chiyoda Ku, Tokyo 1018430, Japan

[3] Grad Univ Adv Studies Sokendai, Hayama, Japan

[4] YAMAHA Corp, Shizuoka 4380192, Japan

来源：

2014 14TH INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC) | 2014年

关键词：

Speech enhancement; ad-hoc microphone array; sampling frequency mismatch; nonnegative matrix factorization; time-frequency masking; SEPARATION;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this paper, we investigate amplitude-based speech enhancement for asynchronous distributed recording. In an ad-hoc microphone array context, it is supposed that different asynchronous devices record speech. As a result, the phase information is unreliable due to sampling frequency mismatch. For speech enhancement based on the amplitude information instead of the phase information, supervised nonnegative matrix factorization (NMF) is introduced in the time-channel domain. The basis vectors, which represents the gain of the transfer function from a source to each microphone, are trained in advance by using single source observation. The experimental evaluations show that this approach is well robust against the sampling frequency mismatch.

引用

页码：203 / 207

页数：5

共 50 条

[1] Wavelet Speech Enhancement Based on Nonnegative Matrix Factorization
Wang, Syu-Siang
Chern, Alan
Tsao, Yu
Hung, Jeih-weih
Lu, Xugang
Lai, Ying-Hui
Su, Borching
[J]. IEEE SIGNAL PROCESSING LETTERS, 2016, 23 (08) : 1101 - 1105
[2] Speech Enhancement Based on Codebook Constrained Nonnegative Matrix Factorization
Bai, Zhigang
Bao, Changchun
Yan, Bofang
[J]. 2018 INTERNATIONAL CONFERENCE ON AUDIO, LANGUAGE AND IMAGE PROCESSING (ICALIP), 2018, : 361 - 365
[3] SPEECH ENHANCEMENT USING SEGMENTAL NONNEGATIVE MATRIX FACTORIZATION
Fan, Hao-Teng
Hung, Jeih-weih
Lu, Xugang
Wang, Syu-Siang
Tsao, Yu
[J]. 2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
[4] Research on Speech Enhancement Based on Nonnegative Matrix Factorization and Improved Genetic Algorithm
Wang Wenqi
Zhang Hongjin
Fu Shan
[J]. PROCEEDINGS OF THE 35TH CHINESE CONTROL CONFERENCE 2016, 2016, : 4950 - 4954
[5] Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization
Mohammadiha, Nasser
Smaragdis, Paris
Leijon, Arne
[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2013, 21 (10): : 2140 - 2151
[6] SPEECH ENHANCEMENT USING NONNEGATIVE MATRIX FACTORIZATION WITH TEMPORAL CONTINUITY
Nam, Seung-Hyon
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2015, 34 (03): : 240 - 246
[7] Speech enhancement based on nonnegative matrix factorization in constant-Q frequency domain
Xu, Longting
Wei, Zhilin
Zaidi, Syed Faham Ali
Ren, Bo
Yang, Jichen
[J]. APPLIED ACOUSTICS, 2021, 174
[8] Speech Enhancement Using Convolutive Nonnegative Matrix Factorization with Cosparsity Regularization
Mirbagheri, Majid
Xu, Yanbo
Akram, Sahar
Shamma, Shihab
[J]. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 456 - 459
[9] 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
[10] A NEW LINEAR MMSE FILTER FOR SINGLE CHANNEL SPEECH ENHANCEMENT BASED ON NONNEGATIVE MATRIX FACTORIZATION
Mohammadiha, Nasser
Gerkmann, Timo
Leijon, Arne
[J]. 2011 IEEE WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS (WASPAA), 2011, : 45 - 48

← 1 2 3 4 5 →