Tomoko MATSUI


Comparative Study of Speaker Identification Methods: dPLRM, SVM and GMM
Tomoko MATSUI Kunio TANABE 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3  pp. 1066-1073
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speaker Recognition
Keyword: 
speaker recognitionspeaker identificationkernel machinedual penalized logistic regression machinesupport vector machineGaussian mixture model
 Summary | Full Text:PDF(1.2MB)

Dialogue Speech Recognition by Combining Hierarchical Topic Classification and Language Model Switching
Ian R. LANE Tatsuya KAWAHARA Tomoko MATSUI Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 446-454
Type of Manuscript:  Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Spoken Language Systems
Keyword: 
speech recognitiontopic detectiontopic-dependent language modelingsupport vector machinesmulti-domain spoken dialogue
 Summary | Full Text:PDF(578.2KB)

Verification of Multi-Class Recognition Decision: A Classification Approach
Tomoko MATSUI Frank K. SOONG Biing-Hwang JUANG 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 455-462
Type of Manuscript:  Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Spoken Language Systems
Keyword: 
2-class classifierdiscriminative trainingN-best hypothesisword verification
 Summary | Full Text:PDF(592KB)

Automatic Generation of Non-uniform HMM Topologies Based on the MDL Criterion
Takatoshi JITSUHIRO Tomoko MATSUI Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2004/08/01
Vol. E87-D  No. 8  pp. 2121-2129
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech recognitionacoustic modeltopology trainingMDL criterionSSS algorithm
 Summary | Full Text:PDF(1.2MB)

Robust Model for Speaker Verification against Session-Dependent Utterance Variation
Tomoko MATSUI Kiyoaki AIKAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2003/04/01
Vol. E86-D  No. 4  pp. 712-718
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speaker verificationspeaker modelsession dependent utterance variationhandset dependent distortion
 Summary | Full Text:PDF(221.7KB)

A Study on Acoustic Modeling of Pauses for Recognizing Noisy Conversational Speech
Jin-Song ZHANG Konstantin MARKOV Tomoko MATSUI Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2003/03/01
Vol. E86-D  No. 3  pp. 489-496
Type of Manuscript:  Special Section PAPER (Special Issue on Speech Information Processing)
Category: Robust Speech Recognition and Enhancement
Keyword: 
conversational speech recognitioninter-word pausecontext dependent HMMsprosodic phrase boundary
 Summary | Full Text:PDF(390.8KB)

Noise and Channel Distortion Robust ASR System for DARPA SPINE2 Task
Konstantin MARKOV Tomoko MATSUI Rainer GRUHN Jinsong ZHANG Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2003/03/01
Vol. E86-D  No. 3  pp. 497-504
Type of Manuscript:  Special Section PAPER (Special Issue on Speech Information Processing)
Category: Robust Speech Recognition and Enhancement
Keyword: 
noise robustnessonline adaptationhypothesis combinationrobust features
 Summary | Full Text:PDF(457.6KB)