Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
EA, ASJ-H |
2021-07-16 11:30 |
Online |
Online |
A study on the number of speech samples required for making acoustic models in tailor-made speech synthesis Keigo Narita, Naofumi Aoki, Atsuhito Udo, Yoshinori Dobashi (Hokkaido Univ.) EA2021-16 |
In this study, we created speaker dependent acoustic models with varying numbers of samples, and confirmed differences i... [more] |
EA2021-16 pp.75-76 |
SP, IPSJ-SLP (Joint) |
2018-07-26 17:15 |
Shizuoka |
Sago-Royal-Hotel (Hamamatsu) |
Knowledge Distillation from Neural Network Based Acoustic Model based on Different Decision Tree Takashi Fukuda, Samuel Thomas (IBM) SP2018-20 |
This paper proposes a method to transfer acoustic knowledge from teacher network with a different decision tree to a stu... [more] |
SP2018-20 pp.21-24 |
SIP, EA, SP, MI (Joint) [detail] |
2018-03-20 09:00 |
Okinawa |
|
[Poster Presentation]
Performance evaluation of unknown sound clustering for indoor-environmental sound classification based on self-generated acoustic model Sakiko Mishima, Yukoh Wakabayashi, Takahiro Fukumori, Keisuke Imoto, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.) EA2017-152 SIP2017-161 SP2017-135 |
Indoor-environmental sound classification is useful for surveillance systems which monitor the situations in the dark an... [more] |
EA2017-152 SIP2017-161 SP2017-135 pp.277-280 |
NLC, IPSJ-NL, SP, IPSJ-SLP (Joint) [detail] |
2017-12-21 12:50 |
Tokyo |
Waseda Univ. Green Computing Systems Research Organization |
[Poster Presentation]
Development of Speaker/Environment-Dependent Acoustic Model for Non-Audible Murmur Recognition Based on DNN Adaptation Seita Noda, Tomoki Hayashi, Tomoki Toda, Kazuya Takeda (Nagoya Univ.) SP2017-56 |
In this research, we aim to improve the performance of non-audible murmur (NAM) recognition towards the development of s... [more] |
SP2017-56 pp.7-10 |
SP, SIP, EA |
2017-03-01 12:40 |
Okinawa |
Okinawa Industry Support Center |
[Poster Presentation]
Indoor-environmental sound identification based on deep neural network with higher-dimensional features Sakiko Mishima, Yukoh Wakabayashi, Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura (Ritsumeikan Univ.) EA2016-87 SIP2016-142 SP2016-82 |
Surveillance systems with a video camera have been utilized for the safety of people. It is important to identify the in... [more] |
EA2016-87 SIP2016-142 SP2016-82 pp.31-36 |
SP, SIP, EA |
2017-03-01 12:40 |
Okinawa |
Okinawa Industry Support Center |
[Poster Presentation]
An investigation of speaker adaptation method for DNN-based speech synthesis using speaker codes Nobukatsu Hojo, Yusuke Ijima (NTT) EA2016-108 SIP2016-163 SP2016-103 |
In this work, we conducted objective evaluation experiments on the conventional speaker adaptation methods for DNN-based... [more] |
EA2016-108 SIP2016-163 SP2016-103 pp.147-152 |
SP, SIP, EA |
2017-03-02 09:00 |
Okinawa |
Okinawa Industry Support Center |
[Poster Presentation]
Study of branch selecting DNN acoustic model for robustness to environmental variation Takafumi Moriya, Taichi Asami, Yoshikazu Yamaguchi, Yushi Aono (NTT) EA2016-131 SIP2016-186 SP2016-126 |
The performance of speech recognition tasks can be significantly improved by the use of deep neural networks (DNN). Spee... [more] |
EA2016-131 SIP2016-186 SP2016-126 pp.277-282 |
SP |
2017-01-21 16:35 |
Tokyo |
The University of Tokyo |
Simultaneous modeling of acoustic feature sequences and its temporal structures for DNN-based speech synthesis Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) SP2016-76 |
In statistical parametric speech synthesis, a hidden Markov model (HMM) is widely used as an acoustic model. Recently, d... [more] |
SP2016-76 pp.71-76 |
SP |
2016-10-27 16:00 |
Shizuoka |
Shizuoka University. |
Word modeling for end-to-end Japanese speech recognition Hitoshi Ito, Aiko Hagiwara, Manon Ichiki, Takeshi Mishima, Shoei Sato (NHK), Akio Kobayashi (NES) SP2016-47 |
In this paper, we propose a novel modeling for end-to-end Japanese speech recognition using Deep Neural Networks(DNN). W... [more] |
SP2016-47 pp.31-36 |
PRMU, IPSJ-CVIM, IBISML [detail] |
2016-09-05 16:45 |
Toyama |
|
Acoustic event detection and removal using LSTM-CTC for speech recognition Yu Nasu (former Toshiba), Hiroshi Fujimura (Toshiba) PRMU2016-69 IBISML2016-24 |
Deep learning techniques have drastically increased the speech recognition performance. However, there are few practical... [more] |
PRMU2016-69 IBISML2016-24 pp.121-126 |
SP |
2016-08-24 14:00 |
Kyoto |
ACCMS, Kyoto Univ. |
[Invited Talk]
Unsupervised Music Understanding based on Hierarchical Bayesian Acoustic and Language Models Kazuyoshi Yoshii (Kyoto Univ.) SP2016-29 |
This paper presents a statistical approach to unsupervised music understanding. Our goal is to estimate musical notes fr... [more] |
SP2016-29 pp.13-18 |
SP, IPSJ-SLP (Joint) |
2016-07-28 14:00 |
Yamagata |
Takinoyu Hotel |
Evaluation of Japanese English DNN Acoustic Models with English Level Yuta Kawachi, Hirokazu Masataki, Taichi Asami, Yushi Aono (NTT) SP2016-20 |
In this paper, we propose an acoustic model that takes into consideration foreign language fluency level by extracting a... [more] |
SP2016-20 pp.1-6 |
SP, IPSJ-SLP (Joint) |
2016-07-28 15:45 |
Yamagata |
Takinoyu Hotel |
On the Use of Speaker Codes for Multi-Speaker Modeling in DNN-based Speech Synthesis Nobukatsu Hojo, Yusuke Ijima (NTT), Hideyuki Mizuno (Tokyo University of Science, Suwa) SP2016-22 |
Recent studies have shown that DNN-based speech synthesis can generate more natural synthesized speech than the conventi... [more] |
SP2016-22 pp.13-18 |
SP |
2015-08-21 16:15 |
Iwate |
Iwate Prefectural Univ. |
Training Data Selection for Acoustic Modeling Based on Submodular Optimization of Joint KL Divergence Taichi Asami, Ryo Masumura, Hirokazu Masataki, Manabu Okamoto, Sumitaka Sakauchi (NTT) SP2015-58 |
This paper provides a novel training data selection method to
construct acoustic models for automatic speech recogniti... [more] |
SP2015-58 pp.45-50 |
SP, IPSJ-SLP (Joint) |
2015-07-16 15:10 |
Nagano |
Katakura Suwako Hotel |
A study on discriminative approach for estimation of the divergence between distributions and its application to language identification Yosuke Kashiwagi, Congying Zhang, Daisuke Saito, Nobuaki Minematsu (Tokyo Univ.) SP2015-38 |
In this paper, we propose a method for estimating the statistical divergence between probability distributions by a disc... [more] |
SP2015-38 pp.13-18 |
SP, IPSJ-SLP (Joint) |
2015-07-17 09:30 |
Nagano |
Katakura Suwako Hotel |
Multiple Feed-forward Deep Neural Networks for Statistical Parametric Speech Synthesis Shinji Takaki (NII), SangJin Kim (Naver Labs), Junichi Yamagishi (NII), JongJin Kim (Naver Labs) SP2015-44 |
In this paper, we investigate a combination of several feed-forward deep neural networks (DNNs) for a high-quality stati... [more] |
SP2015-44 pp.49-54 |
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 |
NLC, IPSJ-NL, SP, IPSJ-SLP, JSAI-SLUD (Joint) [detail] |
2014-12-16 11:00 |
Kanagawa |
Tokyo Institute of Technology (Suzukakedai Campus) |
Speaker adaptation using speaker-normalized DNN based on speaker codes Yosuke Kashiwagi, Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) SP2014-118 |
Recently, deep neural network (DNN) becomes one of the main streams of acoustic modeling for automatic speech recognitio... [more] |
SP2014-118 pp.105-110 |
SP, IPSJ-MUS |
2014-05-24 11:30 |
Tokyo |
|
Native language recognition using machine learning Ryota Sakagami, Kouki Takeshita, Longbiao Wang, Masahiro Iwahashi (Nagaoka Univ. of Tech) SP2014-13 |
The difference in pronunciation occurs in a non-native speaker and a native speaker. Therefore, communication is difficu... [more] |
SP2014-13 pp.139-141 |
SP |
2014-02-28 10:30 |
Tokushima |
The University of Tokushima |
Evaluation of reverberant speech recognition by selecting suitable acoustic model with acoustic parameters Takahiro Fukumori, Masato Nakayama, Takanobu Nishiura, Yoichi Yamashita (Ritsumeikan Univ.) SP2013-108 |
The reverberant speech degrades the speech recognition performance in the field of distant-talking speech. As one of app... [more] |
SP2013-108 pp.7-12 |