Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EA |
2019-12-13 13:25 |
Fukuoka |
Kyushu Inst. Tech. |
Rank-constrained spatial covariance matrix estimation based on multivariate complex generalized Gaussian distribution and its acceleration for blind speech extraction Yuki Kubo, Norihiro Takamune (UTokyo), Daichi Kitamura (NIT, Kagawa), Hiroshi Saruwatari (UTokyo) EA2019-78 |
In this paper, we generalize a generative model in rank-constrained spatial covariance matrix estimation that separates ... [more] |
EA2019-78 pp.85-92 |
EA |
2013-07-19 15:15 |
Hokkaido |
Health Sci. Univ. of Hokkaido |
Evaluation of musical-noise-free blind speech extraction under nonstationary noise environment Ryoichi Miyazaki, Hiroshi Saruwatari, Satoshi Nakamura, Kiyohiro Shikano (NAIST), Kazunobu Kondo (YAMAHA) EA2013-51 |
We have already proposed a musical-noise-free blind speech extraction method using a microphone array that can be applie... [more] |
EA2013-51 pp.105-110 |
EA |
2013-07-19 15:45 |
Hokkaido |
Health Sci. Univ. of Hokkaido |
Semi-Blind Optimization Scheme of Joint Suppression of Background Noise and Late Reverberation Fine D. Aprilyanti, Hiroshi Saruwatari, Kiyohiro Shikano, Satoshi Nakamura (NAIST), Tomoya Takatani (Toyota) EA2013-52 |
Recently, a method to jointly suppress diffuse background noise and late reverberation part of speech has been proposed,... [more] |
EA2013-52 pp.111-116 |
SP, EA, SIP |
2013-05-16 17:20 |
Okayama |
|
Analysis on musical noise generation for blind speech extraction based on generalized MMSE short-time spectral amplitude estimator Shunsuke Nakai, Suzumi Kanehara, Ryoichi Miyazaki, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST) EA2013-13 SIP2013-13 SP2013-13 |
In this paper, we give an analysis on the amount of musical noise for blind speech extraction based on a generalized mi... [more] |
EA2013-13 SIP2013-13 SP2013-13 pp.73-78 |
EA |
2012-06-08 13:40 |
Shizuoka |
Yamaha Co. |
Blind speech extraction for non-audible murmur speech with speaker's movement noise Miyuki Itoi, Ryoichi Miyazaki, Tomoki Toda, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST) EA2012-40 |
In this paper, we address an improvement method of noise reduction used in multichannel Non-Audible Murmur (NAM) based o... [more] |
EA2012-40 pp.43-48 |
EA, US (Joint) |
2012-01-26 13:00 |
Osaka |
Kansai Univ. |
Evaluation of Blind Speech Extraction for Speech Archiving of Poster Session Kodai Okamoto, Ryoichi Miyazaki, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST) EA2011-107 |
In this report, we propose a 19-channel microphone array recording system used for blind speech extraction and diarizati... [more] |
EA2011-107 pp.19-24 |
EA |
2009-07-17 14:30 |
Tokyo |
|
Blind Signal Extraction Based on Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator Ryoi Okamoto, Yu Takahashi, Hiroshi Saruwatari, Kiyohiro Shikano (Nara Inst. of Sci and Tech.) EA2009-39 |
In this paper, we propose a new blind speech extraction method consisting of a minimum mean-square error short-time spec... [more] |
EA2009-39 pp.13-18 |
SIP, EA |
2008-05-29 16:15 |
Osaka |
Kansai Univ. |
Development of Hands-Free Spoken Dialogue System with Real-Time Blind Spatial Subtraction Array Yu Takahashi, Keiichi Osako, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST) EA2008-16 SIP2008-25 |
In this paper, we construct a hands-free robot spoken dialogue system based on the real-time blind spatial subtraction
... [more] |
EA2008-16 SIP2008-25 pp.59-64 |
EA |
2007-09-28 14:00 |
Nara |
Nara Institute of Science and Technology |
Fast Algorithm for Cancellation of Near Point Source Based on Independent Component Analysis Keiichi Osako, Yu Takahashi, Yoshimitsu Mori, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST) EA2007-57 |
In this paper, we propose a fast algorithm for cancellation of near point source based on independent component analysis... [more] |
EA2007-57 pp.13-18 |
EA |
2004-12-10 15:55 |
Tokyo |
|
Pitch extraction of noisy speech using noise reduction processing and cosine modulation of autocorrelation coefficients sequence Keita Ogawa, Takeshi Fukabayashi (Shizuoka Univ.) |
It is well known that pitch extraction of noisy speech is difficult due to the effect of noise. Therefore, we propose a ... [more] |
EA2004-114 pp.65-70 |