Taichi ASAMI


Domain Adaptation Based on Mixture of Latent Words Language Models for Automatic Speech Recognition
Ryo MASUMURA Taichi ASAMI Takanobu OBA Hirokazu MASATAKI Sumitaka SAKAUCHI Akinori ITO 
Publication:   
Publication Date: 2018/06/01
Vol. E101-D  No. 6  pp. 1581-1590
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
domain adaptationmixture modelinglatent words language modelslatent variable spaceautomatic speech recognition
 Summary | Full Text:PDF(792.7KB)

Investigation of Combining Various Major Language Model Technologies including Data Expansion and Adaptation
Ryo MASUMURA Taichi ASAMI Takanobu OBA Hirokazu MASATAKI Sumitaka SAKAUCHI Akinori ITO 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2452-2461
Type of Manuscript:  Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Language modeling
Keyword: 
language modelsdirect decodingunsupervised adaptationrescoringspontaneous speech recognition
 Summary | Full Text:PDF(333.7KB)

N-gram Approximation of Latent Words Language Models for Domain Robust Automatic Speech Recognition
Ryo MASUMURA Taichi ASAMI Takanobu OBA Hirokazu MASATAKI Sumitaka SAKAUCHI Satoshi TAKAHASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2462-2470
Type of Manuscript:  Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Language modeling
Keyword: 
language modelsdomain robustnesslatent words language modelsn-gram approximationautomatic speech recognition
 Summary | Full Text:PDF(539.2KB)

Evaluation of a Noise-Robust Multi-Stream Speaker Verification Method Using F0 Information
Taichi ASAMI Koji IWANO Sadaoki FURUI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/03/01
Vol. E91-D  No. 3  pp. 549-557
Type of Manuscript:  Special Section PAPER (Special Section on Robust Speech Processing in Realistic Environments)
Category: Speaker Verification
Keyword: 
speaker verificationF0 informationmulti-stream HMMsstream-weight and threshold optimizationAdaboost
 Summary | Full Text:PDF(473KB)