Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
PRMU |
2022-09-15 10:00 |
Kanagawa |
(Primary: On-site, Secondary: Online) |
One-cut Network Pruning at Initialization with Explainable Image Concepts Yinan Yang (Rits Univ.), Ying Ji (Nagoya Univ.), Yu Wang (Hitotsubashi Univ.), Jien Kato (Rits Univ.) PRMU2022-18 |
Recent research investigates the feasibility of one-cut network pruning at initialization (OPAI). SNIP and GraSP are tw... [more] |
PRMU2022-18 pp.49-54 |
EA, US, SP, SIP, IPSJ-SLP [detail] |
2021-03-04 10:15 |
Online |
Online |
A quantitative measure of discriminability between NMF dictionaries Eisuke Konno, Daisuke Saito, Nobuaki Minematsu (UTokyo) EA2020-82 SIP2020-113 SP2020-47 |
Supervised nonnegative matrix factorization (NMF) is a popular approach for monaural audio source separation. It realize... [more] |
EA2020-82 SIP2020-113 SP2020-47 pp.134-139 |
SP, IPSJ-SLP (Joint) |
2016-07-30 09:00 |
Yamagata |
Takinoyu Hotel |
Discriminative Training Method of Recurrent Neural Network Language Models for Speech Recognition Yuuki Tachioka (Mitsubishi Electric), Shinji Watanabe (MERL) SP2016-26 |
A recurrent neural network language model (RNN-LM) can consider a longer word context than an n-gram language model, and... [more] |
SP2016-26 pp.33-38 |
SP, IPSJ-SLP (Joint) |
2015-07-16 16:20 |
Nagano |
Katakura Suwako Hotel |
Sequence Discriminative Training for Low-Rank Deep Neural Networks Yuuki Tachioka (Mitsubishi Electric), Shinji Watanabe, Jonathan Le Roux, John Hershey (MERL) SP2015-39 |
Deep neural network (DNN) acoustic models outperform conventional Gaussian mixture model (GMM) but the number of paramet... [more] |
SP2015-39 pp.19-24 |
SP, IPSJ-SLP (Joint) |
2014-07-25 09:30 |
Iwate |
Hotel Hanamaki |
A generalized discriminative training framework for system combination Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John Hershey (Mitsubishi Electric) SP2014-65 |
This paper proposes a generalized discriminative training framework for system combination, which encompasses acoustic m... [more] |
SP2014-65 pp.13-18 |
SP, IPSJ-MUS |
2014-05-25 09:45 |
Tokyo |
|
[Invited Talk]
Machine Translation
-- Why couldn't we do it? Why are we starting to be able to now? -- Graham Neubig (NAIST) SP2014-6 |
While machine translation has been a long-held dream dating back to the appearance of the first computers, for many year... [more] |
SP2014-6 pp.35-38 |
SP, IPSJ-MUS |
2014-05-24 11:30 |
Tokyo |
|
Discriminative training of acoustic models for system combination Yuuki Tachioka (Mitsubishi Electric), Shinji Watanabe, Jonathan Le Roux, John R. Hershey (MERL) SP2014-15 |
In discriminative training methods, the objective function is designed to improve the performance of automatic speech re... [more] |
SP2014-15 pp.147-152 |
SP, IPSJ-SLP (Joint) |
2013-07-25 15:10 |
Miyagi |
Soho (togatta spa) |
Effectiveness of discriminative approaches for speech recognition under noisy environments on the 2nd CHiME Challenge Yuuki Tachioka (Mitsubishi Electric), Shinji Watanabe, Jonathan Le Roux, John R Hershey (MERL) SP2013-55 |
The 2nd CHiME challenge is a difficult two-microphone speech recognition task with non-stationary interference. We inves... [more] |
SP2013-55 pp.13-18 |
SP, IPSJ-SLP (Joint) |
2013-07-26 10:30 |
Miyagi |
Soho (togatta spa) |
Grapheme-to-phoneme Conversion based on Adaptive Regularization of Weight Vectors Keigo Kubo, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura (NAIST) SP2013-57 |
The current state-of-the-art approach in grapheme-to-phoneme (g2p) conversion is structured learning based on the Margin... [more] |
SP2013-57 pp.25-30 |
ITS, IE, ITE-AIT, ITE-HI, ITE-ME [detail] |
2012-02-20 15:40 |
Hokkaido |
Hokkaido Univ. |
Experimental Evaluation of Image Object Tracking Method using Particle Filter and Minimum Classification Error Training Jyun'ichi Nakamura, Shigeru Katagiri, Miho Ohsaki (Doshisha Univ) ITS2011-36 IE2011-112 |
To increase the accuracy of image object tracking, a discriminative tracking method was proposed that combined the parti... [more] |
ITS2011-36 IE2011-112 pp.79-84 |
SP, NLC, IPSJ-SLP [detail] |
2011-12-20 09:25 |
Tokyo |
|
GIF-SP: Improvement of Speech Recognition Using General and Discriminative Feature Satoshi Tamura, Yoji Tagami, Satoru Hayamizu (Gifu Univ.) NLC2011-47 SP2011-92 |
This paper proposes a general and discriminative feature ``GIF''.
The feature extraction method proposed in this paper ... [more] |
NLC2011-47 SP2011-92 pp.119-124 |
SP |
2011-07-22 17:00 |
Hokkaido |
Jozankei Grand Hotel |
[Invited Talk]
The Forefront of Statistical Machine Translation Algorithms Hajime Tsukada (NTT) SP2011-48 |
This talk reviews recent advances of statistical machine translation in this decade. In addition, several newly develope... [more] |
SP2011-48 pp.41-43 |
SP |
2011-06-23 13:00 |
Aichi |
Nagoya Univ. |
[Invited Talk]
Fundamentals and recent research trends in feature extraction Takashi Fukuda (IBM) SP2011-30 |
Cepstral coefficients and their dynamics that represent temporal variations have been widely used for automatic speech r... [more] |
SP2011-30 pp.1-6 |
NC, MBE (Joint) |
2010-03-09 13:45 |
Tokyo |
Tamagawa University |
A Comparison of HHMMs and HHCRFs in State Sequence Estimation Hirotaka Tamada, Akira Hayashi, Nobuo Suematsu, Kazunori Iwata (Hiroshima City Univ.) NC2009-105 |
HMMs (hidden Markov models) are well-known generative models for time series data. Recently, however, CRFs (conditional ... [more] |
NC2009-105 pp.101-106 |
PRMU |
2009-09-01 09:00 |
Miyagi |
Tohoku Univ. |
Implementation and Experimental Evaluation of Ensemble Minimum Classification Error Training Shin'ichi Taniguchi (Doshisha University), Hideyuki Watanabe (NICT), Shigeru Katagiri, Kohta Yamada (Doshisha University), Atsushi Nakamura, Erik McDermott, Shinji Watanabe (NTT), Naho Nishijima, Miho Ohsaki (Doshisha Univ.) PRMU2009-67 |
Recently, we developed a noble Ensemble-based Minimum Classification Error training method (EMCE) by combining the advan... [more] |
PRMU2009-67 pp.103-108 |
SP, NLC |
2008-12-10 16:10 |
Tokyo |
Waseda Univ. |
Discriminative Rescoring Based on Minimization of Word Errors for Speech Recognition Akio Kobayashi, Takahiro Oku, Shinichi Homma, Shoei Sato, Toru Imai, Tohru Takagi (NHK) NLC2008-67 SP2008-122 |
This paper describes a novel method of rescoring that reflects tendencies of errors in word hypotheses in speech recogni... [more] |
NLC2008-67 SP2008-122 pp.255-260 |
NLC |
2008-02-08 15:30 |
Niigata |
Yuzawa Culture Center |
Discriminative topic-sentiment analysis from unsupervised topic corpora Kugatsu Sadamitsu, Takahiro Fukutomi, Mikio Yamamoto (Univ. of Tsukuba) NLC2007-97 |
Topic information included in reviews can be beneficially used in sentiment analysis, and this paper proposes a method o... [more] |
NLC2007-97 pp.57-62 |