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

2017 ◽  
Vol 29 (1) ◽  
pp. 198-212 ◽  
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.

scholarly journals Generalized independent low-rank matrix analysis using heavy-tailed distributions for blind source separation

2018 ◽  
Vol 2018 (1) ◽  
Author(s):  
Daichi Kitamura ◽  
Shinichi Mogami ◽  
Yoshiki Mitsui ◽  
Norihiro Takamune ◽  
Hiroshi Saruwatari ◽  
...  
Keyword(s):  
Blind Source Separation ◽  
Source Separation ◽  
Matrix Analysis ◽  
Low Rank ◽  
Heavy Tailed Distributions ◽  
Rank Matrix ◽  
Heavy Tailed ◽  
Low Rank Matrix

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

2017 ◽  
Vol 2017 (0) ◽  
pp. 1P2-P05 ◽  
Author(s):  
Yoshiaki bando ◽  
Yuichi Ambe ◽  
Katsutoshi Itoyama ◽  
Masashi Konyo ◽  
Satoshi Tadokoro ◽  
...  
Keyword(s):  
Real Time ◽  
Low Rank ◽  
Sparse Decomposition ◽  
Rescue Robot ◽  
Human Voice

A New Analysis of the Iterative Threshold Algorithm for RPCA by Primal-Dual Method

2014 ◽  
Vol 989-994 ◽  
pp. 2462-2466 ◽  
Author(s):  
Ru Ya Fan ◽  
Hong Xia Wang ◽  
Hui Zhang
Keyword(s):  
Gradient Method ◽  
Principal Component ◽  
Low Rank ◽  
Dual Method ◽  
Theoretical Derivation ◽  
Threshold Algorithm ◽  
Rank Matrix ◽  
Primal Dual ◽  
Low Rank Matrix ◽  
Iterative Threshold

This paper studies the iterative threshold algorithm (ITA) for solving the Robust Principal Component Analysis (RPCA) problems, which is to recover a low-rank matrix with a fraction of its entries being arbitrarily corrupted. By utilizing the primal-dual method, we analyze the ITA in a new way and prove that the ITA is essentially equivalent to gradient method applying to a dual problem. In the original ITA, it is hard to choose the parameters and hence it converges very slowly. Now, based on the new insight, existing techniques of the gradient method can be used to accelerate the ITA. We combine the theoretical derivation with the numerical simulation experiments to give an empirical guidance to set the parameters. As illustration, background modeling problem is solved by the ITA with optimal parameters.

Sign in / Sign up

Export Citation Format

Share Document