Yoshinori SAGISAKA


Language Modeling Using Patterns Extracted from Parse Trees for Speech Recognition
Takatoshi JITSUHIRO Hirofumi YAMAMOTO Setsuo YAMADA Genichiro KIKUI Yoshinori SAGISAKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2003/03/01
Vol. E86-D  No. 3  pp. 446-453
Type of Manuscript:  Special Section PAPER (Special Issue on Speech Information Processing)
Category: Speech and Speaker Recognition
Keyword: 
speech recognitionlanguage modeln-gram modelparserpattern model
 Summary | Full Text:PDF(913.3KB)

A Speech Translation System Applied to a Real-World Task/Domain and Its Evaluation Using Real-World Speech Data
Atsushi NAKAMURA Masaki NAITO Hajime TSUKADA Rainer GRUHN Eiichiro SUMITA Hideki KASHIOKA Hideharu NAKAJIMA Tohru SHIMIZU Yoshinori SAGISAKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2001/01/01
Vol. E84-D  No. 1  pp. 142-154
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech translation systemreal-world speechtask-alterationcost evaluation and performance evaluation
 Summary | Full Text:PDF(3.8MB)

Statistical Modelling of Speech Segment Duration by Constrained Tree Regression
Naoto IWAHASHI Yoshinori SAGISAKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2000/07/25
Vol. E83-D  No. 7  pp. 1550-1559
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech segmental durationstatistical modellingregression
 Summary | Full Text:PDF(541.5KB)

Prosodic Characteristics of Japanese Conversational Speech
Nobuyoshi KAIKI Yoshinori SAGISAKA 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1993/11/25
Vol. E76-A  No. 11  pp. 1927-1933
Type of Manuscript:  Special Section PAPER (Special Section on Speech Synthesis: Current Technologies and Thier Application)
Category: 
Keyword: 
prosodyconversationfundamental frequencyamplitudesegmental duration
 Summary | Full Text:PDF(579.8KB)

Speech Segment Selection for Concatenative Synthesis Based on Spectral Distortion Minimization
Naoto IWAHASHI Nobuyoshi KAIKI Yoshinori SAGISAKA 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1993/11/25
Vol. E76-A  No. 11  pp. 1942-1948
Type of Manuscript:  Special Section PAPER (Special Section on Speech Synthesis: Current Technologies and Thier Application)
Category: 
Keyword: 
speech synthesissegment selectiondynamic programmingspectral distortion
 Summary | Full Text:PDF(662.4KB)