Low latency and high quality two-stage human-voice-enhancement system for a hose-shaped rescue robot

Yoshiaki Bando; Hiroshi Saruwatari; Nobutaka Ono; Shoji Makino; Katustoshi Itoyama; Daichi Kitamura; Masaru Ishimura; Moe Takakusaki; Narumi Mae; Kouei Yamaoka; Yutaro Matsui; Yuichi Ambe; Masashi Konyo; Satoshi Tadokoro; Kazuyoshi Yoshii; Hiroshi G. Okuno

doi:10.20965/jrm.2017.p0198

Low latency and high quality two-stage human-voice-enhancement system for a hose-shaped rescue robot

Yoshiaki Bando, Hiroshi Saruwatari, Nobutaka Ono, Shoji Makino, Katustoshi Itoyama, Daichi Kitamura, Masaru Ishimura, Moe Takakusaki, Narumi Mae, Kouei Yamaoka, Yutaro Matsui, Yuichi Ambe, Masashi Konyo, Satoshi Tadokoro, Kazuyoshi Yoshii, Hiroshi G. Okuno

Research output: Contribution to journal › Article › peer-review

9 Citations (Scopus)

Abstract

This paper presents the design and implementation of a two-stage human-voice enhancement system for a hose-shaped rescue robot. When a microphoneequipped hose-shaped robot is used to search for a victim under a collapsed building, human-voice enhancement is crucial because the sound captured by a microphone array is contaminated by the ego-noise of the robot. For achieving both low latency and high quality, our system combines online and offline human-voice enhancement, providing an overview first and then details on demand. The online enhancement is used for searching for a victim in real time, while the offline one facilitates scrutiny by listening to highly enhanced human voices. Our online enhancement is based on an online robust principal component analysis, and our offline enhancement is based on an independent lowrank matrix analysis. The two enhancement methods are integrated with Robot Operating System (ROS). Experimental results showed that both the online and offline enhancement methods outperformed conventional methods.

Original language	English
Pages (from-to)	198-212
Number of pages	15
Journal	Journal of Robotics and Mechatronics
Volume	29
Issue number	1
DOIs	https://doi.org/10.20965/jrm.2017.p0198
Publication status	Published - 2017 Feb
Externally published	Yes

Keywords

Blind human-voice enhancement
Hose-shaped rescue robot
Robot audition
Search and rescue

ASJC Scopus subject areas

Computer Science(all)
Electrical and Electronic Engineering

Access to Document

10.20965/jrm.2017.p0198

Cite this

Bando, Y., Saruwatari, H., Ono, N., Makino, S., Itoyama, K., Kitamura, D., Ishimura, M., Takakusaki, M., Mae, N., Yamaoka, K., Matsui, Y., Ambe, Y., Konyo, M., Tadokoro, S., Yoshii, K., & Okuno, H. G. (2017). Low latency and high quality two-stage human-voice-enhancement system for a hose-shaped rescue robot. Journal of Robotics and Mechatronics, 29(1), 198-212. https://doi.org/10.20965/jrm.2017.p0198

Bando, Y, Saruwatari, H, Ono, N, Makino, S, Itoyama, K, Kitamura, D, Ishimura, M, Takakusaki, M, Mae, N, Yamaoka, K, Matsui, Y, Ambe, Y, Konyo, M, Tadokoro, S, Yoshii, K & Okuno, HG 2017, 'Low latency and high quality two-stage human-voice-enhancement system for a hose-shaped rescue robot', Journal of Robotics and Mechatronics, vol. 29, no. 1, pp. 198-212. https://doi.org/10.20965/jrm.2017.p0198

@article{db4733b14d2d40e2a2925fb72357dec4,

title = "Low latency and high quality two-stage human-voice-enhancement system for a hose-shaped rescue robot",

abstract = "This paper presents the design and implementation of a two-stage human-voice enhancement system for a hose-shaped rescue robot. When a microphoneequipped hose-shaped robot is used to search for a victim under a collapsed building, human-voice enhancement is crucial because the sound captured by a microphone array is contaminated by the ego-noise of the robot. For achieving both low latency and high quality, our system combines online and offline human-voice enhancement, providing an overview first and then details on demand. The online enhancement is used for searching for a victim in real time, while the offline one facilitates scrutiny by listening to highly enhanced human voices. Our online enhancement is based on an online robust principal component analysis, and our offline enhancement is based on an independent lowrank matrix analysis. The two enhancement methods are integrated with Robot Operating System (ROS). Experimental results showed that both the online and offline enhancement methods outperformed conventional methods.",

keywords = "Blind human-voice enhancement, Hose-shaped rescue robot, Robot audition, Search and rescue",

author = "Yoshiaki Bando and Hiroshi Saruwatari and Nobutaka Ono and Shoji Makino and Katustoshi Itoyama and Daichi Kitamura and Masaru Ishimura and Moe Takakusaki and Narumi Mae and Kouei Yamaoka and Yutaro Matsui and Yuichi Ambe and Masashi Konyo and Satoshi Tadokoro and Kazuyoshi Yoshii and Okuno, {Hiroshi G.}",

note = "Funding Information: This study was partially supported by ImPACT Tough Robotics Challenge and by JSPS KAKENHI No. 24220006 and No. 15J08765. Publisher Copyright: {\textcopyright} 2017, Fuji Technology Press. All rights reserved.",

year = "2017",

month = feb,

doi = "10.20965/jrm.2017.p0198",

language = "English",

volume = "29",

pages = "198--212",

journal = "Journal of Robotics and Mechatronics",

issn = "0915-3942",

publisher = "Fuji Technology Press",

number = "1",

}

TY - JOUR

T1 - Low latency and high quality two-stage human-voice-enhancement system for a hose-shaped rescue robot

AU - Bando, Yoshiaki

AU - Saruwatari, Hiroshi

AU - Ono, Nobutaka

AU - Makino, Shoji

AU - Itoyama, Katustoshi

AU - Kitamura, Daichi

AU - Ishimura, Masaru

AU - Takakusaki, Moe

AU - Mae, Narumi

AU - Yamaoka, Kouei

AU - Matsui, Yutaro

AU - Ambe, Yuichi

AU - Konyo, Masashi

AU - Tadokoro, Satoshi

AU - Yoshii, Kazuyoshi

AU - Okuno, Hiroshi G.

N1 - Funding Information: This study was partially supported by ImPACT Tough Robotics Challenge and by JSPS KAKENHI No. 24220006 and No. 15J08765. Publisher Copyright: © 2017, Fuji Technology Press. All rights reserved.

PY - 2017/2

Y1 - 2017/2

N2 - This paper presents the design and implementation of a two-stage human-voice enhancement system for a hose-shaped rescue robot. When a microphoneequipped hose-shaped robot is used to search for a victim under a collapsed building, human-voice enhancement is crucial because the sound captured by a microphone array is contaminated by the ego-noise of the robot. For achieving both low latency and high quality, our system combines online and offline human-voice enhancement, providing an overview first and then details on demand. The online enhancement is used for searching for a victim in real time, while the offline one facilitates scrutiny by listening to highly enhanced human voices. Our online enhancement is based on an online robust principal component analysis, and our offline enhancement is based on an independent lowrank matrix analysis. The two enhancement methods are integrated with Robot Operating System (ROS). Experimental results showed that both the online and offline enhancement methods outperformed conventional methods.

AB - This paper presents the design and implementation of a two-stage human-voice enhancement system for a hose-shaped rescue robot. When a microphoneequipped hose-shaped robot is used to search for a victim under a collapsed building, human-voice enhancement is crucial because the sound captured by a microphone array is contaminated by the ego-noise of the robot. For achieving both low latency and high quality, our system combines online and offline human-voice enhancement, providing an overview first and then details on demand. The online enhancement is used for searching for a victim in real time, while the offline one facilitates scrutiny by listening to highly enhanced human voices. Our online enhancement is based on an online robust principal component analysis, and our offline enhancement is based on an independent lowrank matrix analysis. The two enhancement methods are integrated with Robot Operating System (ROS). Experimental results showed that both the online and offline enhancement methods outperformed conventional methods.

KW - Blind human-voice enhancement

KW - Hose-shaped rescue robot

KW - Robot audition

KW - Search and rescue

UR - http://www.scopus.com/inward/record.url?scp=85013960126&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013960126&partnerID=8YFLogxK

U2 - 10.20965/jrm.2017.p0198

DO - 10.20965/jrm.2017.p0198

M3 - Article

AN - SCOPUS:85013960126

SN - 0915-3942

VL - 29

SP - 198

EP - 212

JO - Journal of Robotics and Mechatronics

JF - Journal of Robotics and Mechatronics

IS - 1

ER -

Low latency and high quality two-stage human-voice-enhancement system for a hose-shaped rescue robot

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this