Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SP |
2011-01-27 15:45 |
Kyoto |
NICT |
Relation between musical noise generation in nonlinear signal processing and speech recognition performance Ryoichi Miyazaki, Takayuki Inoue, Nobuhisa Hirata, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST), Tomoya Takatani (TOYOTA) SP2010-106 |
In this paper, we discuss a relation between musical noise generation in nonlinear signal processing and
speech recogni... [more] |
SP2010-106 pp.19-24 |
SP |
2011-01-27 17:00 |
Kyoto |
NICT |
Noise reduction using a small microphone array for speech recognition Tomohiro Narita, Tomohiro Iwasaki (Mitsubishi Electric Corp.) SP2010-108 |
This paper addresses a noise reduction method using a stereo microphone array. Most of noises in car are defused and we ... [more] |
SP2010-108 pp.31-36 |
SP |
2011-01-28 11:30 |
Kyoto |
NICT |
A study of subtraction coefficient optimization for sound quality improvement with spectral subtraction Keisuke Horii, Takahiro Fukumori, Masanori Morise, Takanobu Nishiura, Yoichi Yamashita (Ritsumeikan Univ.) SP2010-113 |
In this paper, we'll explain sound quality improvement with Spectral Subtraction (SS).
SS is generally used because i... [more] |
SP2010-113 pp.59-64 |
EA |
2010-06-11 11:00 |
Hokkaido |
Health Sci. Univ. of Hokkaido |
Mathematical metric of amount of musical noise in recursive spectral subtraction Takayuki Inoue, Hiroshi Saruwatari, Yu Takahashi, Kiyohiro Shikano (NAIST), Kazunobu Kondo (Yamaha Corporate Research and Development Center) EA2010-30 |
In this paper, we provide a new theoretical analysis of the amount of musical noise generated via iterative spectral sub... [more] |
EA2010-30 pp.47-52 |
SP, EA, SIP |
2010-05-26 16:25 |
Hyogo |
Konan Univ. (Hirao Seminar House) |
Mathematical metric of musical noise in arbitrary exponent domain SS Takayuki Inoue, Yu Takahashi, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST), Kazunobu Kondo (Center for Advanced Sound Techonogies, Yamaha Corp) EA2010-7 SIP2010-7 SP2010-7 |
In this paper, we provide a new theoretical analysis of the amount of musical noise generated via generalized spectral s... [more] |
EA2010-7 SIP2010-7 SP2010-7 pp.37-42 |
SP, EA, SIP |
2010-05-26 16:50 |
Hyogo |
Konan Univ. (Hirao Seminar House) |
Musical tone reduction on iterative spectral subtraction based on optimum flooring parameters Takahiro Fukumori, Masanori Morise, Takanobu Nishiura (Ritsumeikan Univ.), Hiroaki Nanjo (Ryukoku Univ.) EA2010-8 SIP2010-8 SP2010-8 |
Spectral subtraction (SS) is the effective method used to reduce the noise from the speech recorded in the noisy environ... [more] |
EA2010-8 SIP2010-8 SP2010-8 pp.43-48 |
EA, SIP, SP |
2009-05-28 14:15 |
Hyogo |
|
Musical-noise regulation for combination method of channel-domain nonlinear speech enhancement and adaptive array signal processing Yohei Ishiskawa, Yu Takahashi, Hiroshi Saruwatari, Kiyohiro Shikano (Nara Inst. of Sci and Tech.), Kazunobu Kondo (Yamaha Corp.) EA2009-3 SIP2009-3 SP2009-8 |
Recently, many integration methods of linear microphone array signal
processing and nonlinear signal processing for noi... [more] |
EA2009-3 SIP2009-3 SP2009-8 pp.11-16 |
EA, US (Joint) |
2009-01-30 11:00 |
Kyoto |
|
Objective sound quality comparison based on higher-order statistics for nonlinear noise reduction methods Yoshihisa Uemura, Yu Takahashi, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST), Kazunobu Kondo (Yamaha) EA2008-127 |
In this paper, we reveal new findings about the generated musical noise in minimum mean-square error short-time spectral... [more] |
EA2008-127 pp.67-72 |
EA, US (Joint) |
2009-01-30 11:25 |
Kyoto |
|
Objective sound quality evaluation for combination method of beamforming and spectral subtraction Yu Takahashi, Keiichi Osako, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST), Kazunobu Kondo (Yamaha) EA2008-128 |
In this paper, we conduct an analysis for reduction of musical noise in integration method of microphone array signal p... [more] |
EA2008-128 pp.73-78 |
EA |
2008-11-21 14:45 |
Oita |
|
Sound source segregation based on the frequency domain binaural model for a binaural hearing assistance system
-- Musical noise reduction using time-frequency filtering -- Ryouji Kawano, Yoshifumi Chisaki, Tsuyoshi Usagawa (Kumamoto Univ.) EA2008-98 |
The frequency domain binaural model (FDBM) has been studied as the basic processing model of a binaural hearing assistan... [more] |
EA2008-98 pp.81-86 |
EA |
2008-07-18 17:00 |
Nara |
|
Relationship between logarithmic kurtosis ratio and degree of musical noise generation on spectral subtraction Yoshihisa Uemura, Yu Takahashi, Hiroshi Saruwatari, Kiyohiro Shikano (NAIST), Kazunobu Kondo (YAMAHA) EA2008-44 |
In this paper, we propose a mathematical metric of the amount of musical noise generated in spectral subtraction. Spectr... [more] |
EA2008-44 pp.43-48 |