Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EA, ASJ-H |
2019-08-09 10:30 |
Miyagi |
Tohoku Univ. |
Study on Robust Method for Blindly Estimating Speech Transmission Index using Convolutional Neural Network with Temporal Amplitude Envelope Suradej Doungpummet (JAIST), Jessada Karunjana (NASDA), Waree Kongprawechnon (SIIT), Masashi Unoki (JAIST) EA2019-30 |
We have developed a robust scheme for blindly estimating speech transmission index (STI) in noisy reverberant environmen... [more] |
EA2019-30 pp.47-52 |
ISEC, SITE, ICSS, EMM, HWS, BioX, IPSJ-CSEC, IPSJ-SPT [detail] |
2019-07-24 12:10 |
Kochi |
Kochi University of Technology |
Recording device identification based on audio distortion depending on system-on-chip Akira Nishimura (Tokyo Univ. Info. Sci.) ISEC2019-48 SITE2019-42 BioX2019-40 HWS2019-43 ICSS2019-46 EMM2019-51 |
This study addresses device-specific distortion observed in recorded
audio, to identify a built-in system-on-a-chip (... [more] |
ISEC2019-48 SITE2019-42 BioX2019-40 HWS2019-43 ICSS2019-46 EMM2019-51 pp.311-316 |
EA, SIP, SP |
2019-03-14 10:25 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
Blind speech separation based on approximate joint diagonalization utilizing correlation between neighboring frequency bins Taiki Asamizu, Toshihiro Furukawa (TUS) EA2018-100 SIP2018-106 SP2018-62 |
In this paper, we propose a new method that extends the approximate joint diagonalization blind speech separation (BSS).... [more] |
EA2018-100 SIP2018-106 SP2018-62 pp.7-12 |
EA, SIP, SP |
2019-03-14 13:30 |
Nagasaki |
i+Land nagasaki (Nagasaki-shi) |
[Poster Presentation]
Initial analysis of emotional speech acted in noise Yi Zhao (NII), Atsushi Ando (NTT), Shinji Takaki, Junichi Yamagishi (NII), Satoshi Kobashikawa (NTT) EA2018-120 SIP2018-126 SP2018-82 |
Speakers usually adjust their way of talking in noisy environments involuntarily for effective communication, this adapt... [more] |
EA2018-120 SIP2018-126 SP2018-82 pp.125-130 |
EA, ASJ-H, EMM, IPSJ-MUS [detail] |
2018-11-22 10:00 |
Ishikawa |
Hotel Koshuen |
[Invited Talk]
Phase reconstruction for speech enhancement and its effect on array processing Yukoh Wakabayashi (TMU) EA2018-80 EMM2018-80 |
Phase spectrum processing for speech enhancement, so called ``phase reconstruction,'' has been particularly received att... [more] |
EA2018-80 EMM2018-80 pp.163-168 |
IEE-CMN, EMM, LOIS, IE, ITE-ME [detail] |
2018-09-28 13:40 |
Oita |
Beppu Int'l Convention Ctr. aka B-CON Plaza |
Study on speech representation for speech fingerprint using perceptual matching-pursuit algorithm Dung Kim Tran, Huy Quoc Nguyen, Masashi Unoki (JAIST) LOIS2018-20 IE2018-40 EMM2018-59 |
Recent studies have revealed the weakness of audio fingerprinting methods in speech signals. The problem is that spectro... [more] |
LOIS2018-20 IE2018-40 EMM2018-59 pp.71-76 |
EA, ASJ-H |
2018-08-23 12:55 |
Miyagi |
Tohoku Gakuin Univ. |
Self-produced speech enhancement and suppression method with wearable air- and body-conductive microphones Moe Takada, Shogo Seki, Tomoki Toda (Nagoya Univ.) EA2018-29 |
This paper presents a self-produced speech enhancement and suppression method for multichannel signals recorded with bot... [more] |
EA2018-29 pp.7-12 |
EA, ASJ-H, ASJ-AA |
2018-07-25 13:40 |
Hokkaido |
Hokkaido Univ. |
Interference-free power spectral representations of periodic sounds and their application to VOCODERs Hideki Kawahara (Wakayama Univ.), Masanori Morise (Univ. Yamanashi), Kanru Hua (Univ. Illinois) EA2018-23 |
We propose a method to calculate the spectral envelope of voiced sounds for VOCODER applications. In our previous techni... [more] |
EA2018-23 pp.135-140 |
PRMU, SP |
2018-06-29 10:00 |
Nagano |
|
Revisiting interference-free power spectral representations of periodic signals Hideki Kawahara (Wakayama Univ.), Masanori Morise (Univ. Yamanashi), Kanru Hua (Univ. Illinois) PRMU2018-29 SP2018-9 |
We propose two algorithms to calculate interference-free power spectra of periodic signals. This set of algorithms is ou... [more] |
PRMU2018-29 SP2018-9 pp.41-46 |
SIP, EA, SP, MI (Joint) [detail] |
2018-03-20 09:00 |
Okinawa |
|
[Poster Presentation]
Speech Enhancement Using Non-Local Means Kyohei Mitani, Yosuke Sugiura, Tetsuya Shimamura (Saitama Univ.) EA2017-142 SIP2017-151 SP2017-125 |
In this paper, we propose a speech enhance method using Non-Local Means. In the proposed method, we focus on Non-Local M... [more] |
EA2017-142 SIP2017-151 SP2017-125 pp.227-230 |
EA |
2018-02-16 13:10 |
Hiroshima |
Pref. Univ. Hiroshima |
The effect of increasing the number of channels with multi-channel non-negative matrix factorization for noisy speech recognition Takanobu Uramoto (Oita Univ.), Youhei Okato, Toshiyuki Hanazawa (Mitsubishi Electric), Iori Miura, Shingo Uenohara, Ken'ich Furuya (Oita Univ.) EA2017-99 |
Nonnegative Matrix Factorization (NMF) factorizes a non-negative matrix into two non-negative matrices. In the field of ... [more] |
EA2017-99 pp.33-38 |
SP, ASJ-H |
2018-01-20 13:00 |
Tokyo |
The University of Tokyo |
An extended log domain pulse model for VOCODERs Hideki Kawahara (Wakayama Univ.) SP2017-66 |
We propose a new procedure to design excitation source signals for the analysis-and-synthesis systems without preserving... [more] |
SP2017-66 pp.1-4 |
SIS |
2017-12-14 10:50 |
Tottori |
Tottori Prefectural Center for Lifelong Learning |
Harmonic Structure Detection in Speech Separation Using Modified DFT Pair Based on ASA Motohiro Ichikawa, Isao Nakanishi (Tottori Univ) SIS2017-34 |
Humans have the ability of cocktail party effect to be able to recognized the target voice from the various conversation... [more] |
SIS2017-34 pp.5-9 |
EA, ASJ-H |
2017-10-21 14:30 |
Toyama |
Ushidake-Onsen |
Study on modulation spectrum analysis for speech and non-speech signals Takuto Isoyama, Masashi Unoki (JAIST) EA2017-49 |
This paper aims to clarify available features for discriminating and classifying speech and non-speech signals.Modulatio... [more] |
EA2017-49 pp.29-34 |
SP |
2017-08-30 11:00 |
Kyoto |
Kyoto Univ. |
[Poster Presentation]
Semi-blind speech separation and enhancement using recurrent neural network Masaya Wake, Yoshiaki Bando, Masato Mimura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara (Kyoto Univ.) SP2017-22 |
This paper describes a semi-blind speech enhancement method using a neural network.
In a human-robot speech interaction... [more] |
SP2017-22 pp.13-18 |
SITE, EMM, ISEC, ICSS, IPSJ-CSEC, IPSJ-SPT [detail] |
2017-07-15 13:25 |
Tokyo |
|
Investigation of spikegram-based signal representation for speech fingerprints Dung Kim Tran, Masashi Unoki (JAIST) ISEC2017-32 SITE2017-24 ICSS2017-31 EMM2017-35 |
This paper investigates the ability of spikegrams in representing the speech content and voice identications of speech s... [more] |
ISEC2017-32 SITE2017-24 ICSS2017-31 EMM2017-35 pp.241-246 |
SP, SIP, EA |
2017-03-02 09:00 |
Okinawa |
Okinawa Industry Support Center |
[Poster Presentation]
Individuality-Preserving HMM Sound Synthesis System for Articulation Disorders Reina Ueda (Kobe Univ.), Tetsuya Takiguchi (Kobe Univ./JST PRESTO), Yasuo Ariki (Kobe Univ.) EA2016-136 SIP2016-191 SP2016-131 |
This paper presents a speech synthesis method for a person with an articulation disorder resulting from the athetoid typ... [more] |
EA2016-136 SIP2016-191 SP2016-131 pp.301-306 |
TL |
2016-12-17 16:30 |
Tokyo |
Room 303/304/305, Building #8, Waseda University |
Sincerity Condition Revisited: Truth or Dare? Sachiko Shudo (Waseda Univ.) TL2016-56 |
Some speech acts, such as apologizing and thanking, involve psychological states of the speaker. The relationships betwe... [more] |
TL2016-56 pp.101-104 |
EA, EMM |
2016-11-18 09:40 |
Oita |
Compal Hall (Oita) |
Singular-Spectrum-Analysis-Based Speech Watermarking for Tampering Detection Jessada Karnjana, Masashi Unoki (JAIST) EA2016-57 EMM2016-63 |
This paper proposes a novel speech-tampering-detection scheme by using the semi-fragile watermarking based on the singul... [more] |
EA2016-57 EMM2016-63 pp.55-60 |
EA, EMM |
2016-11-18 10:45 |
Oita |
Compal Hall (Oita) |
Quality estimation of speech masking system using subjective and objective evaluation scores. Yosuke Kobayashi (Muroran Inst. of Tech.), Kazuhiro Kondo (Yamagata Univ.) EA2016-59 EMM2016-65 |
Currently, speech masking systems make use of pre-recorded speech signals to generate maskers. Our previous report, we p... [more] |
EA2016-59 EMM2016-65 pp.67-72 |