Naoto IWAHASHI

Discriminating Unknown Objects from Known Objects Using Image and Speech Information
Yuko OZASA Mikio NAKANO Yasuo ARIKI Naoto IWAHASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2015/03/01
Vol. E98-D  No. 3  pp. 704-711
Type of Manuscript:  PAPER
Category: Multimedia Pattern Processing
Keyword: 
multimodality, unknown object discrimination, object recognition, information integration, 
 Summary | Full Text:PDF
Interactive Learning of Spoken Words and Their Meanings Through an Audio-Visual Interface
Naoto IWAHASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/02/01
Vol. E91-D  No. 2  pp. 312-321
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
mutli-modal interface, word acquisition, multi-media processing, interactive learning, active learning, word meaning, 
 Summary | Full Text:PDF
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 duration, statistical modelling, regression, 
 Summary | Full Text:PDF
Training Method for Pattern Classifier Based on the Performance after Adaptation
Naoto IWAHASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2000/07/25
Vol. E83-D  No. 7  pp. 1560-1566
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
classifier adaptation training optimization, 
 Summary | Full Text:PDF
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 synthesis, segment selection, dynamic programming, spectral distortion, 
 Summary | Full Text:PDF