Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EA, SIP, SP, IPSJ-SLP [detail] |
2022-03-01 14:45 |
Okinawa |
(Primary: On-site, Secondary: Online) |
Target speaker extraction based on conditional variational autoencoder and directional information in underdetermined condition Rui Wang, Li Li, Tomoki Toda (Nagoya Univ) EA2021-76 SIP2021-103 SP2021-61 |
This paper deals with a dual-channel target speaker extraction problem in underdetermined conditions. A blind source sep... [more] |
EA2021-76 SIP2021-103 SP2021-61 pp.76-81 |
SP, IPSJ-SLP, IPSJ-MUS |
2021-06-18 13:00 |
Online |
Online |
F0 estimation of speech based on l2-norm regularized TV-CAR analysis Keiichi Funaki (Univ. of the Ryukyus) SP2021-2 |
Linear Prediction (LP) is the most successful speech analysis in speech processing, including speech coding implemented
... [more] |
SP2021-2 pp.7-12 |
SP, IPSJ-SLP, IPSJ-MUS |
2021-06-19 13:00 |
Online |
Online |
Study on the background cancellation system for speech privacy Jiangning Huang, Akinori Ito (Tohoku Univ.) SP2021-14 |
Evacuation centers at the time of disaster do not have sufficient sound insulation to maintain sound privacy. In this st... [more] |
SP2021-14 pp.57-62 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-03 13:05 |
Online |
Online |
[Invited Talk]
* Masahito Togami (LINE) EA2020-64 SIP2020-95 SP2020-29 |
Recently, deep learning based speech source separation has been evolved rapidly. A neural network (NN) is usually learne... [more] |
EA2020-64 SIP2020-95 SP2020-29 pp.27-32 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-03 14:05 |
Online |
Online |
[Poster Presentation]
A unified source-filter network for neural vocoder Reo Yoneyama, Yi-Chiao Wu, Tomoki Toda (Nagoya Univ.) EA2020-69 SIP2020-100 SP2020-34 |
In this paper, we propose a method to develop a neural vocoder using a single network based on the source-filter theory.... [more] |
EA2020-69 SIP2020-100 SP2020-34 pp.57-62 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-03 14:05 |
Online |
Online |
[Poster Presentation]
Noise-robust time-domain speech separation with basis signals for noise Kohei Ozamoto (Tokyo Tech), Koji Iwano (TCU), Kuniaki Uto, Koichi Shinoda (Tokyo Tech) EA2020-70 SIP2020-101 SP2020-35 |
Recently, speech separation using deep learning has been extensively studied. TasNet, a time-domain method that directly... [more] |
EA2020-70 SIP2020-101 SP2020-35 pp.63-67 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-04 16:10 |
Online |
Online |
Estimation of imagined speech from electrocorticogram with an encoder-decoder model Kotaro Hayashi, Shuji Komeiji (TUAT), Takumi Mitsuhashi, Yasushi Iimura, Hiroharu Suzuki, Hidenori Sugano (Juntendo Univ.), Koichi Shinoda (TokyoTech), Toshihisa Tanaka (TUAT) EA2020-87 SIP2020-118 SP2020-52 |
Recent advances in signal processing and machine learning technologies have made it possible to estimate and reconstruct... [more] |
EA2020-87 SIP2020-118 SP2020-52 pp.164-169 |
EA |
2020-12-14 10:05 |
Online |
Online |
Speech Signal Detection Based on Bayesian Estimation by Observing Air-Conducted Speech under Existence of Surrounding Noise with Aid of Bone-Conducted Speech Akira Ikuta, Hisako Orimoto (Prefectural Univ. of Hiroshima), Kouji Hasegawa (Hiroshima Prefectural Technology Research Inst.) EA2020-48 |
When applying speech recognition systems to actual circumstances such as inspection and maintenance operations in indust... [more] |
EA2020-48 pp.13-18 |
HIP |
2020-10-09 16:45 |
Online |
Online |
Using Pupillary Responses to Measure Cognitive Load of Japanese Synthetic Speech mixed with Noise Mateusz Dubiel (UniStrath), Minoru Nakayama (Tokyo Tech.), Xin Wang (NII) HIP2020-51 |
Pupillometry has recently been introduced as a method to evaluate cognitive workload of synthetic speech. Prior research... [more] |
HIP2020-51 pp.93-96 |
SIS |
2020-03-06 14:40 |
Saitama |
Saitama Hall (Cancelled but technical report was issued) |
An implusive noise detection method in noisy speech signals using the short time Fourier transform Sho Hasegawa, Eisuke Horita (Kanazawa Univ.) SIS2019-58 |
The short-time Fourier transform based method to detect impulsive noises from speech signals is expressed. Especially W... [more] |
SIS2019-58 pp.119-124 |
NC, MBE (Joint) |
2020-03-05 14:35 |
Tokyo |
University of Electro Communications (Cancelled but technical report was issued) |
Detection of covert-speech-related potentials Sho Tsukiyama, Toshimasa Yamazaki (KIT) MBE2019-87 |
Recently, Brain-Computer Interfaces (BCIs) using speeches for communications have been researched by electroencephalogra... [more] |
MBE2019-87 pp.35-40 |
SP, EA, SIP |
2020-03-02 09:20 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Investigation of neural speech rate conversion with multi-speaker WaveNet vocoder Takuma Okamoto (NICT), Keisuke Matsubara (Kobe Univ./NICT), Tomoki Toda (Nagoya Univ./NICT), Yoshinori Shiga, Hisashi Kawai (NICT) EA2019-101 SIP2019-103 SP2019-50 |
Speech rate conversion technology, which can expand or compress speech waveforms without changing pitch of sound, is con... [more] |
EA2019-101 SIP2019-103 SP2019-50 pp.1-6 |
SP, EA, SIP |
2020-03-02 13:00 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Data augmentation for ASR system by using locally time-reversed speech
-- Temporal inversion of feature sequence -- Takanori Ashihara, Tomohiro Tanaka, Takafumi Moriya, Ryo Masumura, Yusuke Shinohara, Makio Kashino (NTT) EA2019-110 SIP2019-112 SP2019-59 |
Data augmentation is one of the techniques to mitigate overfitting and improve robustness against several acoustic varia... [more] |
EA2019-110 SIP2019-112 SP2019-59 pp.53-58 |
SP, EA, SIP |
2020-03-03 09:00 |
Okinawa |
Okinawa Industry Support Center (Cancelled but technical report was issued) |
Semi-supervised Self-produced Speech Enhancement and Suppression Based on Joint Source Modeling of Air- and Body-conducted Signals Using Variational Autoencoder Shogo Seki, Moe Takada, Kazuya Takeda, Tomoki Toda (Nagoya Univ.) EA2019-140 SIP2019-142 SP2019-89 |
This paper proposes a semi-supervised method for enhancing and suppressing self-produced speech, using a variational aut... [more] |
EA2019-140 SIP2019-142 SP2019-89 pp.225-230 |
EMM |
2020-01-27 13:00 |
Miyagi |
Tohoku Univ. |
Suppression of Dialog System Speech by Embedding Marker Signal into High Frequency Band Shunsuke Saga, Akinori Ito (Tohoku Univ.) EMM2019-94 |
Spoken dialog systems have become popular and are used in a home environment, such as smart speakers. A problem will occ... [more] |
EMM2019-94 pp.1-6 |
EA |
2019-12-12 14:25 |
Fukuoka |
Kyushu Inst. Tech. |
Performance improvement of speech enhancement network by multitask learning including noise information Haruki Tanaka (NITTC), Yosuke Sugiura, Nozomiko Yasui, Tetsuya Shimamura (Saitama Univ.), Ryoichi Miyazaki (NITTC) EA2019-70 |
In the signal processing field, there is a growing interest in speech enhancement.Recently, a lot of speech enhancement ... [more] |
EA2019-70 pp.31-36 |
EA |
2019-12-13 11:20 |
Fukuoka |
Kyushu Inst. Tech. |
Listening difficulty rating prediction model using STOI-type objective intelligibility index for outdoor public address speech Keita Noguchi, Yosuke Kobayashi, Jay Kishigami (Muroran-IT), Kiyohiro Kurisu (TOA) EA2019-76 |
An outdoor public address (PA) system is indispensable for emergency broadcasting during the occurrence of disasters, an... [more] |
EA2019-76 pp.71-78 |
NLC, IPSJ-NL, SP, IPSJ-SLP (Joint) [detail] |
2019-12-06 13:55 |
Tokyo |
NHK Science & Technology Research Labs. |
[Poster Presentation]
Time-Varying Complex AR speech analysis based on l2-norm regularization Keiichi Funaki (Univ. of the Ryukyus) SP2019-41 |
Linear prediction (LP) is a mathematical operation estimating an all-pole spectrum from the speech
signal. It is an ess... [more] |
SP2019-41 pp.73-77 |
WIT, SP |
2019-10-27 09:00 |
Kagoshima |
Daiichi Institute of Technology |
Extraction of linguistic representation and syllable recognition from EEG signal of speech-imagery Kentaro Fukai, Hidefumi Ohmura, Kouichi Katsurada (Tokyo Univ. of Science), Satoka Hirata, Yurie Iribe (Aichi Prefectural Univ.), Mingchua Fu, Ryo Taguchi (Nagoya Inst. of Technology), Tsuneo Nitta (Waseda Univ./Toyohashi Univ. of Technology) SP2019-28 WIT2019-27 |
Speech imagery recognition from Electroencephalogram (EEG) is one of the challenging technologies for non-invasive brain... [more] |
SP2019-28 WIT2019-27 pp.63-68 |
WIT, SP |
2019-10-27 09:20 |
Kagoshima |
Daiichi Institute of Technology |
Word Recognition using word likelihood vector from speech-imagery EEG Satoka Hirata, Yurie Iribe (Aichi Prefectual Univ.), Kentaro Fukai, Kouichi Katsurada (Tokyo Univ. of Science), Tsuneo Nitta (Waseda Univ./Toyohashi Univ. of Tech.) SP2019-29 WIT2019-28 |
Previous research suggests that humans manipulate the machine using their electroencephalogram called BCI (Brain Compute... [more] |
SP2019-29 WIT2019-28 pp.69-73 |