Atsunori OGAWA

Feature Based Domain Adaptation for Neural Network Language Models with Factorised Hidden Layers
Michael HENTSCHEL Marc DELCROIX Atsunori OGAWA Tomoharu IWATA Tomohiro NAKATANI 
Publication:   
Publication Date: 2019/03/01
Vol. E102-D  No. 3  pp. 598-608
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
language model, LSTM, domain adaptation, unsupervised, latent Dirichlet allocation, 
 Summary | Full Text:PDF(1.7MB)
Automatic Vocabulary Adaptation Based on Semantic and Acoustic Similarities
Shoko YAMAHATA Yoshikazu YAMAGUCHI Atsunori OGAWA Hirokazu MASATAKI Osamu YOSHIOKA Satoshi TAKAHASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/06/01
Vol. E97-D  No. 6  pp. 1488-1496
Type of Manuscript:  Special Section PAPER (Special Section on Advances in Modeling for Real-world Speech Information Processing and its Application)
Category: Speech Recognition
Keyword: 
out-of-vocabulary, vocabulary adaptation, semantic similarity, acoustic similarity, 
 Summary | Full Text:PDF(1.1MB)
Efficient Combination of Likelihood Recycling and Batch Calculation for Fast Acoustic Likelihood Calculation
Atsunori OGAWA Satoshi TAKAHASHI Atsushi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2011/03/01
Vol. E94-D  No. 3  pp. 648-658
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
fast acoustic likelihood calculation, state likelihood recycling, batch state likelihood calculation, combined acceleration technique, acoustic backing-off, 
 Summary | Full Text:PDF(823.2KB)