Koichi SHINODA


Error Correction Using Long Context Match for Smartphone Speech Recognition
Yuan LIANG Koji IWANO Koichi SHINODA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2015/11/01
Vol. E98-D  No. 11  pp. 1932-1942
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech recognitionerror correctionmultimodal interfaceword confusion networkcontext match
 Summary | Full Text:PDF(674KB)

Spectral Subtraction Based on Non-extensive Statistics for Speech Recognition
Hilman PARDEDE Koji IWANO Koichi SHINODA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2013/08/01
Vol. E96-D  No. 8  pp. 1774-1782
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
robust speech recognitionspectral subtractionGaussian distributionq-Gaussianmaximum likelihood
 Summary | Full Text:PDF(551KB)

Active Learning Using Phone-Error Distribution for Speech Modeling
Hiroko MURAKAMI Koichi SHINODA Sadaoki FURUI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/10/01
Vol. E95-D  No. 10  pp. 2486-2494
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
active learningspeaker adaptationacoustic modelingphone error distributionKullback-Leibler divergence
 Summary | Full Text:PDF(1.1MB)

Online Speaker Clustering Using Incremental Learning of an Ergodic Hidden Markov Model
Takafumi KOSHINAKA Kentaro NAGATOMO Koichi SHINODA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/10/01
Vol. E95-D  No. 10  pp. 2469-2478
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
HMMmodel selectionmeeting recognitionvariational Bayesian learning
 Summary | Full Text:PDF(465.7KB)

Robust Gait-Based Person Identification against Walking Speed Variations
Muhammad Rasyid AQMAR Koichi SHINODA Sadaoki FURUI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/02/01
Vol. E95-D  No. 2  pp. 668-676
Type of Manuscript:  PAPER
Category: Image Recognition, Computer Vision
Keyword: 
gait recognitionCHLAC featuresGSP featureshidden Markov models
 Summary | Full Text:PDF(1.9MB)

Committee-Based Active Learning for Speech Recognition
Yuzo HAMANAKA Koichi SHINODA Takuya TSUTAOKA Sadaoki FURUI Tadashi EMORI Takafumi KOSHINAKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2011/10/01
Vol. E94-D  No. 10  pp. 2015-2023
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
active learningquery by committeeLVCSRprogressive alignment
 Summary | Full Text:PDF(584KB)

Acoustic Model Adaptation for Speech Recognition
Koichi SHINODA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/09/01
Vol. E93-D  No. 9  pp. 2348-2362
Type of Manuscript:  INVITED PAPER (Special Section on Processing Natural Speech Variability for Improved Verbal Human-Computer Interaction)
Category: 
Keyword: 
speech recognitionacoustic model adaptationhidden Markov models
 Summary | Full Text:PDF(311.2KB)

Robust Scene Extraction Using Multi-Stream HMMs for Baseball Broadcast
Nguyen Huu BACH Koichi SHINODA Sadaoki FURUI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/09/01
Vol. E89-D  No. 9  pp. 2553-2561
Type of Manuscript:  PAPER
Category: Image Processing and Video Processing
Keyword: 
CBVIRHMMscene extractiongame adaptation
 Summary | Full Text:PDF(1MB)