Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EA |
2022-05-13 13:10 |
Online |
Online |
Fast Blind Source Separation in Noisy Reverberant Environments Using Independent Vector Extraction Rintaro Ikeshita, Tomohiro Nakatani (NTT) EA2022-5 |
Blind source separation (BSS) is a technique of separating and extracting individual source signals only from their mixt... [more] |
EA2022-5 pp.20-25 |
EA, SIP, SP, IPSJ-SLP [detail] |
2022-03-01 13:10 |
Okinawa |
(Primary: On-site, Secondary: Online) |
The upper limit of subjective intelligibility score of speech enhancement using IRM
-- comparison between laboratory and crowdsourcing experiments -- Ayako Yamamoto, Toshio Irino (Wakayama Univ.), Shoko Araki, Kenichi Arai, Atsunori Ogawa, Keisuke Kinoshita, Tomohiro Nakatani (NTT) EA2021-74 SIP2021-101 SP2021-59 |
We performed subjective speech intelligibility experiments in a laboratory and using crowdsourcing to get a fundamental ... [more] |
EA2021-74 SIP2021-101 SP2021-59 pp.64-69 |
SP, IPSJ-SLP, IPSJ-MUS |
2021-06-18 15:00 |
Online |
Online |
Speech Intelligibility Experiments using crowdsourcing
-- from designing Web page to Data screening -- Ayako Yamamoto, Toshio Irino (Wakayama Univ.), Kenichi Arai, Shoko Araki, Atsunori Ogawa, Keisuke Kinoshita, Tomohiro Nakatani (NTT) SP2021-5 |
Many subjective experiments have been performed to develop objective speech intelligibility measures, but the novel coro... [more] |
SP2021-5 pp.25-30 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-03 14:05 |
Online |
Online |
[Poster Presentation]
Comparison of speech intelligibility results between laboratory and crowd-sourcing experiments Ayako Yamamoto, Toshio Irino (Wakayama Univ.), Kenichi Arai, Shoko Araki, Atunori Ogawa, Keisuke Kinoshita, Tomohiro Nakatani (NTT) EA2020-73 SIP2020-104 SP2020-38 |
Many subjective experiments have been performed to develop objective speech intelligibility measure. But COVID-19 has ma... [more] |
EA2020-73 SIP2020-104 SP2020-38 pp.79-84 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-04 16:45 |
Online |
Online |
Evaluation of Attention Fusion based Audio-Visual Target Speaker Extraction on Real Recordings Hiroshi Sato, Tsubasa Ochiai, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Shoko Araki (NTT) EA2020-88 SIP2020-119 SP2020-53 |
The audio-visual target speech extraction, which aims at extracting a target speaker's voice from a mixture with audio a... [more] |
EA2020-88 SIP2020-119 SP2020-53 pp.170-175 |
SIS, ITE-BCT |
2020-10-02 11:30 |
Online |
Online |
[Invited Talk]
Target speech extraction in speech mixtures with SpeakerBeam Marc Delcroix (NTT), Katerina Zmolikova (BUT), Keisuke Kinoshita, Tsubasa Ochiai, Tomohiro Nakatani, Shoko Araki (NTT) SIS2020-26 |
[more] |
SIS2020-26 pp.81-82 |
SIP |
2020-08-27 11:10 |
Online |
Online |
[Invited Talk]
Recent advances in conversational speech recognition
-- source separation, diarizatoin, and end-to-end speech recognition -- Keisuke Kinoshita, Marc Delcroix (NTT), Thilo von Neumann (PUB), Tomohiro Nakatani, Shoko Araki (NTT) SIP2020-29 |
[more] |
SIP2020-29 pp.9-10 |
SP, EA, SIP |
2020-03-02 11:10 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
[Invited Talk]
Target speech extraction in speech mixtures with SpeakerBeam Marc Delcroix (NTT), Katerina Zmolikova (BUT), Keisuke Kinoshita, Tsubasa Ochiai, Tomohiro Nakatani, Shoko Araki (NTT) EA2019-105 SIP2019-107 SP2019-54 |
[more] |
EA2019-105 SIP2019-107 SP2019-54 pp.27-28 |
EA, SIP, SP |
2019-03-14 15:15 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
Convergence-guaranteed independent positive semidefinite tensor analysis for blind source separation Kanta Fukushige, Norihiro Takamune (UTokyo), Daichi Kitamura (Kagawa-NICT), Hiroshi Saruwatari (UTokyo), Rintaro Ikeshita, Tomohiro Nakatani (NTT) EA2018-127 SIP2018-133 SP2018-89 |
This paper focuses on independent positive semidefinite tensor analysis (IPSDTA), which is a technique for over-determin... [more] |
EA2018-127 SIP2018-133 SP2018-89 pp.167-172 |
SIP, EA, SP, MI (Joint) [detail] |
2018-03-19 13:00 |
Okinawa |
|
[Poster Presentation]
Intelligibility of speech with additive bubble noise and enhancement under hearing impairment simulation Narumi Ohashi, Naoko Yomura, Katsuhiko Yamamoto (Wakayama Univ.), Shoko Araki, Keisuke Kinoshita, Tomohiro Nakatani (NTT), Toshio Irino (Wakayama Univ.) EA2017-116 SIP2017-125 SP2017-99 |
Subjective experiments were performed to develop speech intelligibility (SI) prediction metrics for both hearing-impaire... [more] |
EA2017-116 SIP2017-125 SP2017-99 pp.87-92 |
SP, SIP, EA |
2017-03-01 16:40 |
Okinawa |
Okinawa Industry Support Center |
[Invited Talk]
An Introduction to Example-based Speech Enhancement and Its Improvements Atsunori Ogawa, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani (NTT) EA2016-114 SIP2016-169 SP2016-109 |
This paper introduces example-based speech enhancement, which is a promising single-channel approach to cope with highly... [more] |
EA2016-114 SIP2016-169 SP2016-109 pp.183-188 |
SP, IPSJ-SLP (Joint) |
2015-07-17 11:10 |
Nagano |
Katakura Suwako Hotel |
[Invited Talk]
Aspects of feature extraction in DNN acoustic models Takuya Yoshioka, Marc Delcroix, Masakiyo Fujimoto, Tomohiro Nakatani (NTT) SP2015-46 |
Since the advent of acoustic models based on deep neural networks (DNNs), a vast amount of efforts have been made to fur... [more] |
SP2015-46 pp.61-65 |
EA |
2014-10-24 14:20 |
Tokyo |
Central Research Laboratory, Hitachi, Ltd. |
[Invited Talk]
Speech enhancement techniques in multi-speaker spontaneous speech recognition for conversation scene analysis Shoko Araki, Takaaki Hori, Tomohiro Nakatani (NTT) EA2014-25 |
This paper illustrates speech enhancement techniques for multi-speaker distant-talk speech recognition, where a conversa... [more] |
EA2014-25 pp.9-14 |
SP, IPSJ-MUS |
2014-05-24 11:30 |
Tokyo |
|
[研究紹介] A spectrogram-patch-input DNN model for detection and classification of acoustic events robust to speech overlapping scenarios Miquel Espi, Masakiyo Fujimoto, Yotaro Kubo, Tomohiro Nakatani (NTT) SP2014-17 |
This paper presents an acoustic event detection and classification method that learns features from spectrogram patches ... [more] |
SP2014-17 pp.171-176 |
EA |
2013-10-11 13:30 |
Kyoto |
NTT CS Lab. |
Source number estimation under reverberant and underdetermined conditions based on clustering of source activity sequences Nobutaka Ito, Ingrid Jafari, Shoko Araki, Tomohiro Nakatani (NTT) EA2013-66 |
[more] |
EA2013-66 pp.17-21 |
SP, EA, SIP |
2013-05-16 10:55 |
Okayama |
|
Permutation-free clustering-based source separation based on time-varying mixture weights Nobutaka Ito, Shoko Araki, Tomohiro Nakatani (NTT) EA2013-2 SIP2013-2 SP2013-2 |
To avoid the permutation problem in clustering-based source separation, we introduce a mixture model with time-varying, ... [more] |
EA2013-2 SIP2013-2 SP2013-2 pp.7-12 |
EA |
2012-12-14 10:40 |
Tokyo |
National Institute of Informatics |
Under-Determined Audio Source Separation Based on MAP Spectral Estimation Using Log-Spectral Prior Yasuaki Iwata (Nagoya Univ.), Tomohiro Nakatani, Masakiyo Fujimoto, Takuya Yoshioka (NTT CS Labs), Hirofumi Saito (Nagoya Univ.) EA2012-114 |
Assuming speech to be non-stationary Gaussian process, maximum likelihood spectral estimation has been studied as an eff... [more] |
EA2012-114 pp.29-34 |
EA |
2012-10-28 10:30 |
Toyama |
USHIDAKE resort (Toyama) |
[Invited Talk]
Dereverberation & reverberation control for speech and music signals and its application
-- Making speech clearer and music richer -- Keisuke Kinoshita, Takuya Yoshioka, Tomohiro Nakatani (NTT) EA2012-80 |
The acoustic signals captured by the distant microphones inevitably contain reverberant components due to reflection fro... [more] |
EA2012-80 pp.91-96 |
SP, IPSJ-SLP (Joint) |
2012-07-20 10:00 |
Yamagata |
Hotel Takinoyu (Yamagata Pref.) |
[Invited Talk]
Research on Meeting Analysis and Its Perspective Takaaki Hori, Shoko Araki, Kazuhiro Otsuka, Tomohiro Nakatani, Atsushi Nakamura, Junji Yamato (NTT) SP2012-52 |
[more] |
SP2012-52 pp.13-18 |
SP, NLC, IPSJ-SLP [detail] |
2011-12-20 09:00 |
Tokyo |
|
Simultaneous application of speaker adaptation and noise mixture model estimation for noise suppression Masakiyo Fujimoto, Shinji Watanabe, Tomohiro Nakatani (NTT) NLC2011-46 SP2011-91 |
In this paper, we propose a joint processing method for a model-based noise suppression that simultaneously achieves spe... [more] |
NLC2011-46 SP2011-91 pp.113-118 |