Ego Noise Reduction for Hose-Shaped Rescue Robot Combining Independent Low-Rank Matrix Analysis and Multichannel Noise Cancellation

被引：3

作者：

Mae, Narumi ^{[1
]}

Ishimura, Masaru ^{[1
]}

Makino, Shoji ^{[1
]}

Kitamura, Daichi ^{[2
]}

Ono, Nobutaka ^{[2
,3
]}

Yamada, Takeshi ^{[1
]}

Saruwatari, Hiroshi ^{[4
]}

机构：

[1] Univ Tsukuba, 1-1-1 Tennodai, Tsukuba, Ibaraki 3058573, Japan

[2] SOKENDAI Grad Univ Adv Studies, Hayama, Kanagawa 2400193, Japan

[3] Natl Inst Informat, Chiyoda Ku, 2-1-2 Hitotsubashi, Tokyo 1018430, Japan

[4] Univ Tokyo, Bunkyo Ku, 7-3-1 Hongo, Tokyo 1138654, Japan

来源：

LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION (LVA/ICA 2017) | 2017年 / 10169卷

基金：

日本科学技术振兴机构;

关键词：

Rescue robot; Tough environment; Noise reduction; Non-negative matrix factorization; Independent vector analysis; Multichannel noise cancellation; BLIND SOURCE SEPARATION; AUDIO SOURCE SEPARATION; VECTOR ANALYSIS; SPEECH SIGNALS; FACTORIZATION; ICA;

D O I：

10.1007/978-3-319-53547-0_14

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

In this paper, we present an ego noise reduction method for a hose-shaped rescue robot, developed for search and rescue operations in large-scale disasters. It is used to search for victims in disaster sites by capturing their voices with its microphone array. However, ego noises are mixed with voices, and it is difficult to differentiate them from a call for help from a disaster victim. To solve this problem, we here propose a two-step noise reduction method involving the following: (1) the estimation of both speech and ego noise signals from observed multichannel signals by multichannel nonnegative matrix factorization (NMF) with the rank-1 spatial constraint, and (2) the application of multichannel noise cancellation to the estimated speech signal using reference signals. Our evaluations show that this approach is effective for suppressing ego noise.

引用

页码：141 / 151

页数：11

共 21 条

[1] Aichner R., 2006, P ICASSP
[2] [Anonymous], 2009, NONNEGATIVE MATRIX T
[3] Barfuss H., 2014, P HSCMA
[4] Barfuss H, 2014, 2014 14TH INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC), P16, DOI 10.1109/IWAENC.2014.6953315
[5] Deleforge A, 2015, INT CONF ACOUST SPEE, P355, DOI 10.1109/ICASSP.2015.7177990
[6] Hansler E., 2004, ACOUSTIC ECHO NOISE
[7] Hiroe A, 2006, LECT NOTES COMPUT SC, V3889, P601
[8] Ishimura M., 2016, P IWAENC
[9] Statistical Model of Speech Signals Based on Composite Autoregressive System with Application to Blind Source Separation
Kameoka, Hirokazu
Yoshioka, Takuya
Hamamura, Mariko
Le Roux, Jonathan
Kashino, Kunio
[J]. LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION, 2010, 6365 : 245 - 253
[10] Kim T, 2006, LECT NOTES COMPUT SC, V3889, P165

← 1 2 3 →