Human-voice enhancement based on online RPCA for a hose-shaped rescue robot with a microphone array

Low Latency and High Quality Two-Stage Human-Voice-Enhancement System for a Hose-Shaped Rescue Robot

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2017.p0198 ◽

2017 ◽

Vol 29 (1) ◽

pp. 198-212 ◽

Cited By ~ 7

Author(s):

Yoshiaki Bando ◽

◽

Hiroshi Saruwatari ◽

Nobutaka Ono ◽

Shoji Makino ◽

...

Keyword(s):

Microphone Array ◽

Principal Component ◽

Matrix Analysis ◽

Low Rank ◽

Low Latency ◽

High Quality ◽

Two Stage ◽

Rescue Robot ◽

Human Voice ◽

Rank Matrix

[abstFig src='/00290001/19.jpg' width='300' text='Human-voice enhancement system for a hose-shaped robot' ] This paper presents the design and implementation of a two-stage human-voice enhancement system for a hose-shaped rescue robot. When a microphone-equipped 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, providingan 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 low-rank 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.

Download Full-text

Real-Time Human-Voice Enhancement for a Hose-Shaped Rescue Robot Based on Multi-Channel Low-Rank Sparse Decomposition

The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) ◽

10.1299/jsmermd.2017.1p2-p05 ◽

2017 ◽

Vol 2017 (0) ◽

pp. 1P2-P05 ◽

Cited By ~ 1

Author(s):

Yoshiaki bando ◽

Yuichi Ambe ◽

Katsutoshi Itoyama ◽

Masashi Konyo ◽

Satoshi Tadokoro ◽

...

Keyword(s):

Real Time ◽

Low Rank ◽

Sparse Decomposition ◽

Rescue Robot ◽

Human Voice

Download Full-text

Variational Bayesian multi-channel robust NMF for human-voice enhancement with a deformable and partially-occluded microphone array

2016 24th European Signal Processing Conference (EUSIPCO) ◽

10.1109/eusipco.2016.7760402 ◽

2016 ◽

Cited By ~ 4

Author(s):

Yoshiaki Bando ◽

Katsutoshi Itoyama ◽

Masashi Konyo ◽

Satoshi Tadokoro ◽

Kazuhiro Nakadai ◽

...

Keyword(s):

Microphone Array ◽

Variational Bayesian ◽

Human Voice ◽

Partially Occluded

Download Full-text

Subjective Comparison Experiments of DMS and Conventional Stereo

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.719-720.1203 ◽

2015 ◽

Vol 719-720 ◽

pp. 1203-1208

Author(s):

Wei Zhao ◽

Guo Pin Huang ◽

Qin Zhang

Keyword(s):

Microphone Array ◽

Subjective Evaluation ◽

Sound Sources ◽

Training Material ◽

Sound System ◽

Dynamic Matrix ◽

Human Voice ◽

Sound Effects ◽

Channel Input ◽

Huygens Principle

Multi-channel dynamic matrix sound system (DMS) is a multi-channel input and output sound system which is based on source synthesis and Huygens' principle. The sound sources are recorded by microphone array and multi-channel independent recording, instead of the field. This paper describes the results of the subjective evaluation experiments between DMS and conventional stereo system by the semantic differential (SD) method. Five parts of the audio materials and a training material, including the human voice, music, sound effects, were used as the stimuli. All of the stimuli were recorded by the DMS and conventional stereo system respectively. The results proof that the effectiveness of DMS, which has a higher level of sound quality and can give the audience the experience of dynamic subjective feelings compared with conventional stereo system. Furthermore, sound designers must carefully consider the influence of gender, age, preferences on the hearing impression.

Download Full-text