IEICE Technical Committee Submission System
Conference Schedule
Online Proceedings
[Sign in]
š (ESS/̥/쥽/ISS)
Tech. Rep. Archives
š (ES)
    [Japanese] / [English] 
( Committee/Place/Topics  ) --Press->
 
( Paper Keywords:  /  Column:Title Auth. Affi. Abst. Keyword ) --Press->

All Technical Committee Conferences  (All Years)

Search Results: Conference Papers
 Conference Papers (Available on Advance Programs)  (Sort by: Date Descending)
 Results 1 - 12 of 12  /   
Committee Date Time Place Paper Title / Authors Abstract Paper #
PRMU, IPSJ-CVIM, MVE [detail] 2015-01-23
09:50
Nara   Analysis of Minimum Classification Error Training using Bit-String-Based Genetic Algorithms
Hiroto Togoe (Doshisha Univ.), Hideyuki Watanabe (NICT), Shigeru Katagiri (Doshisha Univ.), Xugang Lu, Chiori Hori (NICT), Miho Ohsaki (Doshisha Univ.)
Minimum Classification Error (MCE) training using gradient-descent-based loss minimization does not guarantee a global m... [more] PRMU2014-100 MVE2014-62
pp.171-176
PRMU, IPSJ-CVIM, MVE [detail] 2015-01-23
10:15
Nara   Relation between Data Grouping and Robustness to Unseen Data in Large Geometric Margin Minimum Classification Error Training
Hiroyuki Shiraishi (Doshisha Univ), Hideyuki Watanabe (NICT), Shigeru Katagiri (Doshisha Univ), Xugang Lu, Chiori Hori (NICT), Miho Ohsaki (Doshisha Univ)
To develop a pattern classifier that is robust to unseen pattern samples, classifier parameters have been conventionally... [more] PRMU2014-101 MVE2014-63
pp.177-182
PRMU 2014-03-14
15:30
Tokyo   Experimental study on effect of pre-training in deep learning through visualization of unit outputs
Tsubasa Ochiai (Doshisha Univ./NICT), Hideyuki Watanabe (NICT), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.), Shigeki Matsuda, Chiori Hori (NICT)
To clarify the capability of recent powerful classifier concept, Deep Neural Networks (DNN), we experimentally
investig... [more]
PRMU2013-210
pp.253-258
PRMU, IPSJ-CVIM, MVE [detail] 2014-01-23
09:30
Osaka   Minimum Classification Error Training with Automatic Determination of Loss Smoothness Common to All Classes
Kensuke Ota (Doshisha Univ.), Hideyuki Watanabe (NICT), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.), Shigeki Matsuda, Chiori Hori (NICT)
The smoothness of the smooth classification error count loss used in the Minimum Classification Error (MCE) training has... [more] PRMU2013-91 MVE2013-32
pp.1-6
PRMU, IPSJ-CVIM, MVE [detail] 2014-01-23
10:00
Osaka   Minimum Classification Error Training with Automatic Control of Loss Smoothness
Hideaki Tanaka (Doshisha Univ.), Hideyuki Watanabe (NICT), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.), Shigeki Matsuda, Chiori Hori (NICT)
The Minimum Classification Error (MCE) training has been successfully applied to various types of classifiers. However, ... [more] PRMU2013-92 MVE2013-33
pp.7-12
PRMU, IPSJ-CVIM, MVE [detail] 2014-01-23
10:30
Osaka   Multi-Class Support Vector Machine based on Minimum Classification Error Criterion
Hisashi Uehara (Doshisha Univ.), Hideyuki Watanabe (NICT), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.), Shigeki Matsuda, Chiori Hori (NICT)
Gradient-descent-based optimization methods used in Minimum Classification Error (MCE) training are not necessarily easi... [more] PRMU2013-93 MVE2013-34
pp.13-18
PRMU, IPSJ-CVIM, MVE [detail] 2014-01-23
11:00
Osaka   Large Geometric Margin Minimum Classification Error Training with Automatic Optimization Of The Number of Prototypes
Yuji Takayama (Doshisha Univ.), Hideyuki Watanabe (NICT), Shigeru Katagiri, Miho Ohsaki (Doshisha Univ.), Shigeki Matsuda, Chiori Hori (NICT)
Large Geometric Margin Minimum Classification Error (LGM-MCE) training, which adopts geometric-margin-based misclassific... [more] PRMU2013-94 MVE2013-35
pp.19-24
CNR 2013-10-17
11:00
Osaka Grand Front Osaka rospeex: A Cloud-based Spoken Language Communication Toolkit for ROS
Komei Sugiura, Chiori Hori, Koji Zettsu (NICT)
Stand-alone speech recognition/synthesis engines deployed on robots have
drawbacks in accuracy and quality compared wit... [more]
CNR2013-10
pp.7-10
SP 2011-07-22
14:15
Hokkaido Jozankei Grand Hotel Network-based Spoken Dialog System Development Platform: WFSTDM builder
Chiori Hori, Hisashi Kawai, Hideki Kashioka (NICT)
 [more] SP2011-46
pp.29-34
SP 2009-01-29
15:10
Nara NAIST WFST-based Dialog Management Using Statistical Dialog Model
Chiori Hori, Kiyonori Ohtake, Teruhisa Misu, Hideki Kashioka, Satoshi Nakamura (NICT-ATR)
Abstract We have proposed an expandable and portable dialog scenario description and platform to manage dialog sys-tems... [more] SP2008-130
pp.25-30
NLC 2009-01-27
11:30
Okayama   Constructing Spoken Dialog Corpus for Development Statistical Dialog Management
Hideki Kashioka, Teruhisa Misu, Kiyonori Ohtake, Chiori Hori, Satoshi Nakamura (NICT/ATR)
We are developing two types of dialog system for Kyoto sightseeing task. Our development systems are proto-type system t... [more] NLC2008-78
pp.43-48
SP 2007-05-31
13:00
Kyoto ATR Consolidation-based Speech Translation applied to Chinese-English Broadcast News domain
Chiori Hori (NICT-ATR), Bing Zhao, Stephan Vogel, Alex Waibel (Carnegie Mellon Univ)
The performance of speech translation systems combining automatic speech recognition (ASR) and machine translation (MT) ... [more] SP2007-5
pp.25-30
 Results 1 - 12 of 12  /   
Choose a download format for default settings. [NEW !!]
Text format pLaTeX format CSV format BibTeX format


[Return to Top Page]

[Return to IEICE Home Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan