Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
SIP, EA, SP |
2015-03-02 09:00 |
Okinawa |
|
Wind-induced Noise Reduction in Time Domain Using Closely-aligned Two Microphones. Naoto Sakata, Hirofumi Nakajima (Kogakuin Univ.), Kazuhiro Nakadai (HRI-JP) EA2014-72 SIP2014-113 SP2014-135 |
In this report, wind-induced noise reduction in time domain was investigated using closely-aligned two microphones. A li... [more] |
EA2014-72 SIP2014-113 SP2014-135 pp.1-6 |
SIP, EA, SP |
2015-03-02 09:25 |
Okinawa |
|
Estimation of arrival time differences between direct and reflected sounds from monaural observed signal Taira Onoguchi, Irwansyah, Yoshifumi Chisaki (Kumamoto Univ.) EA2014-73 SIP2014-114 SP2014-136 |
Using arrival time differences between different sound sources, localization of sound sources can be conducted. Reflecte... [more] |
EA2014-73 SIP2014-114 SP2014-136 pp.7-12 |
SIP, EA, SP |
2015-03-02 09:50 |
Okinawa |
|
Unified approach for BSS, DOA estimation, audio event detection and dereverberation with multichannel factorial HMM and DOA mixture model Takuya Higuchi (Univ. of Tokyo), Hirokazu Kameoka (Univ. of Tokyo/ NTT) EA2014-74 SIP2014-115 SP2014-137 |
We deal with the problems of blind source separation, dereverberation, audio event detection and DOA estimation. We prev... [more] |
EA2014-74 SIP2014-115 SP2014-137 pp.13-18 |
SIP, EA, SP |
2015-03-02 10:15 |
Okinawa |
|
Estimating correlation coefficients of two super-Gaussian complex signals without phase observation Shigeki Miyabe (University of Tsukuba), Nobutaka Ono (NII/SOKENDAI), Shoji Makino (University of Tsukuba) EA2014-75 SIP2014-116 SP2014-138 |
[more] |
EA2014-75 SIP2014-116 SP2014-138 pp.19-24 |
SIP, EA, SP |
2015-03-02 10:50 |
Okinawa |
|
Overview of 3GPP Standard EVS Codec
-- High Performance Speech and Audio Coding for VoLTE -- Takehiro Moriya, Yutaka Kamamoto, Noboru Harada (NTT), Kei Kikuiri, Nobuhiko Naka, Kimitaka Tsutsumi, Shinichirou Oosaki (NTT DOCOMO), Hiroyuki Ehara, Takako Sanda, Takuya Kawashima, Seigo Nakao (Panasonic) EA2014-76 SIP2014-117 SP2014-139 |
An international standardization body for mobile communications, 3GPP (3rd generation partnership project), defined a ne... [more] |
EA2014-76 SIP2014-117 SP2014-139 pp.25-30 |
SIP, EA, SP |
2015-03-02 11:15 |
Okinawa |
|
Modulation spectrum-constrained trajectory training algorithm for statistical parametric speech synthesis Shinnosuke Takamichi (NAIST/CMU), Tomoki Toda (NAIST), Alan W. Black (CMU), Satoshi Nakamura (NAIST) EA2014-77 SIP2014-118 SP2014-140 |
[more] |
EA2014-77 SIP2014-118 SP2014-140 pp.31-36 |
SIP, EA, SP |
2015-03-02 11:40 |
Okinawa |
|
Optimization of impulse responses for model training in reverberant speech recognition Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura, Yoichi Yamashita (Ritsumeikan Univ.) EA2014-78 SIP2014-119 SP2014-141 |
The reverberant speech degrades the speech recognition performance in the field of distant-talking speech. As one of app... [more] |
EA2014-78 SIP2014-119 SP2014-141 pp.37-42 |
SIP, EA, SP |
2015-03-02 12:05 |
Okinawa |
|
Visualization of Speech Information by using Animated Texts Yuya Satake, Kazunori Mano (SIT) EA2014-79 SIP2014-120 SP2014-142 |
Speech has para-linguistic information and non-linguistic information. Text, on the other hand, does not include those f... [more] |
EA2014-79 SIP2014-120 SP2014-142 pp.43-48 |
SIP, EA, SP |
2015-03-02 13:30 |
Okinawa |
|
An Approach Combining Organically Noise, SNR and Voice Activity Estimation Masaru Fujieda, Takashi Yazu (OKI) EA2014-80 SIP2014-121 SP2014-143 |
In general, a noise suppression using a single microphone needs signal-to-noise ratio (SNR) in each time-frequency point... [more] |
EA2014-80 SIP2014-121 SP2014-143 pp.49-54 |
SIP, EA, SP |
2015-03-02 13:55 |
Okinawa |
|
Two-Channel Audio Source Separation in Reverberant Conditions Based on Single Voice Activity Segments Atsushi Matsuda, Arata Kawamura, Youji Iiguni (Osaka Univ.) EA2014-81 SIP2014-122 SP2014-144 |
[more] |
EA2014-81 SIP2014-122 SP2014-144 pp.55-60 |
SIP, EA, SP |
2015-03-02 14:20 |
Okinawa |
|
Multiple Sound Source Tracking Based on Sequential Updating Histogram Using 0-1 Reliability Distribution Masato Hirakawa, Kenji Suyama (Tokyo Denki Univ.) EA2014-82 SIP2014-123 SP2014-145 |
[more] |
EA2014-82 SIP2014-123 SP2014-145 pp.61-66 |
SIP, EA, SP |
2015-03-02 14:45 |
Okinawa |
|
Evaluation of Modified Amplitude Modulation Methods in the Parametric Array Loudspeaker Chuang Shi, Yoshinobu Kajikawa (Kansai Univ.) EA2014-83 SIP2014-124 SP2014-146 |
The parametric array loudspeaker is a directional loudspeaker making use of the nonlinearity of air to create a narrow s... [more] |
EA2014-83 SIP2014-124 SP2014-146 pp.67-70 |
SIP, EA, SP |
2015-03-02 15:20 |
Okinawa |
|
[Special Invited Talk]
Active Control of Sound Fields: Enhancing Signals and Attenuating Noise Stephen Elliott (Univ. of Southampton, ISVR) EA2014-84 SIP2014-125 SP2014-147 |
[more] |
EA2014-84 SIP2014-125 SP2014-147 p.71 |
SIP, EA, SP |
2015-03-02 16:10 |
Okinawa |
|
[Special Invited Talk]
Intermediate representation for statistical pattern recognition Koichi Shinoda (TokyoTech) EA2014-85 SIP2014-126 SP2014-148 |
In Deep learning, which has recently seen its boom, it is still not clear how to optimize multi-layer structures. To sol... [more] |
EA2014-85 SIP2014-126 SP2014-148 p.73 |
SIP, EA, SP |
2015-03-03 09:00 |
Okinawa |
|
[Poster Presentation]
RIP Conditions for Exact Recovery of Group-Sparse Vectors under Two Sets of Non-Overlapping Groups Keiji Furuya, Masahiro Yukawa (Keio Univ.), Masao Yamagishi, Isao Yamada (Tokyo Tech.) EA2014-86 SIP2014-127 SP2014-149 |
[more] |
EA2014-86 SIP2014-127 SP2014-149 pp.75-78 |
SIP, EA, SP |
2015-03-03 09:00 |
Okinawa |
|
[Poster Presentation]
Estimation of Feeling based on a Change in Cerebral Bloodflow, using Polynominal Approximation and Difference Miho Asano (The Open Univ. of Japan), Masayuki Nambu (HSI), Masaki Yoshida (Osaka Electro-Communication Univ.), Yasuhiro Kawahara (The Open Univ. of Japan) EA2014-87 SIP2014-128 SP2014-150 |
[more] |
EA2014-87 SIP2014-128 SP2014-150 pp.79-82 |
SIP, EA, SP |
2015-03-03 09:00 |
Okinawa |
|
[Poster Presentation]
A Study on Anomaly Detection Method Using Kalman Filter and Wavelet Transform Motomi Yamaguchi, Keiji Osaki (ICU) EA2014-88 SIP2014-129 SP2014-151 |
Hybrid method of Kalman filtering and wavelet transform is proposed. Error covariance of Kalman filter can be used to e... [more] |
EA2014-88 SIP2014-129 SP2014-151 pp.83-86 |
SIP, EA, SP |
2015-03-03 09:00 |
Okinawa |
|
[Poster Presentation]
Density estimation using proper loss functions Matthew J. Holland, Kazushi Ikeda (NAIST) EA2014-89 SIP2014-130 SP2014-152 |
[more] |
EA2014-89 SIP2014-130 SP2014-152 pp.87-90 |
SIP, EA, SP |
2015-03-03 09:00 |
Okinawa |
|
[Poster Presentation]
MSIST-based Image Restoration with Non-separable Oversampled Lapped Transforms Sho Wakasugi, Shogo Muramatsu (Niigata Univ) EA2014-90 SIP2014-131 SP2014-153 |
This work proposes, an image restoration technique with modified subbsnd-adaptive iterative shrinkage thresholding (MSIS... [more] |
EA2014-90 SIP2014-131 SP2014-153 pp.91-96 |
SIP, EA, SP |
2015-03-03 09:00 |
Okinawa |
|
[Poster Presentation]
A Study on Multiple Exposure Image Fusion with Focus Blur Correction Ryo Matsuoka, Haruki Ishibashi, Tatsuya Baba, Masahiro Okuda (Univ of Kitakyushu) EA2014-91 SIP2014-132 SP2014-154 |
When taking a photograph of a high dynamic range scene by using narrow dynamic range commercial cameras, we often face t... [more] |
EA2014-91 SIP2014-132 SP2014-154 pp.97-102 |