Junichi YAMAGISHI


Preventing Fake Information Generation Against Media Clone Attacks
Noboru BABAGUCHI Isao ECHIZEN Junichi YAMAGISHI Naoko NITTA Yuta NAKASHIMA Kazuaki NAKAMURA Kazuhiro KONO Fuming FANG Seiko MYOJIN Zhenzhong KUANG Huy H. NGUYEN Ngoc-Dung T. TIEU 
Publication:   
Publication Date: 2021/01/01
Vol. E104-D  No. 1  pp. 2-11
Type of Manuscript:  INVITED PAPER (Special Section on Enriched Multimedia — Multimedia Security and Forensics —)
Category: 
Keyword: 
media clonesfake mediamedia processinganonymizationtrusted communication
 Summary | Full Text:PDF(2.8MB)

Generation and Detection of Media Clones
Isao ECHIZEN Noboru BABAGUCHI Junichi YAMAGISHI Naoko NITTA Yuta NAKASHIMA Kazuaki NAKAMURA Kazuhiro KONO Fuming FANG Seiko MYOJIN Zhenzhong KUANG Huy H. NGUYEN Ngoc-Dung T. TIEU 
Publication:   
Publication Date: 2021/01/01
Vol. E104-D  No. 1  pp. 12-23
Type of Manuscript:  INVITED PAPER (Special Section on Enriched Multimedia — Multimedia Security and Forensics —)
Category: 
Keyword: 
media cloneinformation securityimage and speech processingsocial mediacommunication model
 Summary | Full Text:PDF(2.8MB)

Investigation of Using Continuous Representation of Various Linguistic Units in Neural Network Based Text-to-Speech Synthesis
Xin WANG Shinji TAKAKI Junichi YAMAGISHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2471-2480
Type of Manuscript:  Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Speech synthesis
Keyword: 
text-to-speechspeech synthesisrecurrent neural networkcontextsword embedding
 Summary | Full Text:PDF(903KB)

A Style Control Technique for HMM-Based Expressive Speech Synthesis
Takashi NOSE Junichi YAMAGISHI Takashi MASUKO Takao KOBAYASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2007/09/01
Vol. E90-D  No. 9  pp. 1406-1413
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
HMM-based speech synthesisspeaking styleemotional expressionstyle interpolationhidden semi-Markov model (HSMM)multiple-regression HSMM (MRHSMM)
 Summary | Full Text:PDF(914.1KB)

Average-Voice-Based Speech Synthesis Using HSMM-Based Speaker Adaptation and Adaptive Training
Junichi YAMAGISHI Takao KOBAYASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2007/02/01
Vol. E90-D  No. 2  pp. 533-543
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
HMM-based speech synthesisspeaker adaptationspeaker adaptive training (SAT)hidden semi-Markov model (HSMM)maximum likelihood linear regression (MLLR)voice conversion
 Summary | Full Text:PDF(731.1KB)

A Style Adaptation Technique for Speech Synthesis Using HSMM and Suprasegmental Features
Makoto TACHIBANA Junichi YAMAGISHI Takashi MASUKO Takao KOBAYASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3  pp. 1092-1099
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Synthesis
Keyword: 
HMM-based speech synthesisspeaking styleemotional expressionstyle adaptationhidden semi-Markov model (HSMM)maximum likelihood linear regression (MLLR)
 Summary | Full Text:PDF(589.9KB)

Speech Synthesis with Various Emotional Expressions and Speaking Styles by Style Interpolation and Morphing
Makoto TACHIBANA Junichi YAMAGISHI Takashi MASUKO Takao KOBAYASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/11/01
Vol. E88-D  No. 11  pp. 2484-2491
Type of Manuscript:  Special Section PAPER (Special Section on Life-like Agent and its Communication)
Category: 
Keyword: 
HMM-based speech synthesisspeaking styleemotional expressionstyle interpolationstyle morphinghidden semi-Markov model (HSMM)
 Summary | Full Text:PDF(964.3KB)

Human Walking Motion Synthesis with Desired Pace and Stride Length Based on HSMM
Naotake NIWASE Junichi YAMAGISHI Takao KOBAYASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/11/01
Vol. E88-D  No. 11  pp. 2492-2499
Type of Manuscript:  Special Section PAPER (Special Section on Life-like Agent and its Communication)
Category: 
Keyword: 
motion synthesiswalking motionhidden semi-Markov Model (HSMM)HMMfactor adaptive trainingmotion primitivesmotion capture
 Summary | Full Text:PDF(1.7MB)

Acoustic Modeling of Speaking Styles and Emotional Expressions in HMM-Based Speech Synthesis
Junichi YAMAGISHI Koji ONISHI Takashi MASUKO Takao KOBAYASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 502-509
Type of Manuscript:  Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Speech Synthesis and Prosody
Keyword: 
HMM-based speech synthesisexpressive speech synthesisspeaking styleemotional expressionacoustic modelingdecision tree
 Summary | Full Text:PDF(382.6KB)

A Training Method of Average Voice Model for HMM-Based Speech Synthesis
Junichi YAMAGISHI Masatsune TAMURA Takashi MASUKO Keiichi TOKUDA Takao KOBAYASHI 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2003/08/01
Vol. E86-A  No. 8  pp. 1956-1963
Type of Manuscript:  Special Section PAPER (Special Section on Digital Signal Processing)
Category: 
Keyword: 
decision treecontext clusteringspeaker adaptationspeaker adaptive trainingaverage voice modelHMM-based speech synthesis
 Summary | Full Text:PDF(599.3KB)

A Context Clustering Technique for Average Voice Models
Junichi YAMAGISHI Masatsune TAMURA Takashi MASUKO Keiichi TOKUDA Takao KOBAYASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2003/03/01
Vol. E86-D  No. 3  pp. 534-542
Type of Manuscript:  Special Section PAPER (Special Issue on Speech Information Processing)
Category: Speech Synthesis and Prosody
Keyword: 
decision treecontext clusteringaverage voice modelHMM-based speech synthesisspeaker independent model
 Summary | Full Text:PDF(752.9KB)