Kazuya TAKEDA


Investigation of DNN-Based Audio-Visual Speech Recognition
Satoshi TAMURA Hiroshi NINOMIYA Norihide KITAOKA Shin OSUGA Yurie IRIBE Kazuya TAKEDA Satoru HAYAMIZU 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2444-2451
Type of Manuscript:  Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Acoustic modeling
Keyword: 
audio-visual speech recognitiondeep neural networkDeep Bottleneck Featuremulti-stream HMM
 Summary | Full Text:PDF(807.1KB)

Effective Frame Selection for Blind Source Separation Based on Frequency Domain Independent Component Analysis
Yusuke MIZUNO Kazunobu KONDO Takanori NISHINO Norihide KITAOKA Kazuya TAKEDA 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2014/03/01
Vol. E97-A  No. 3  pp. 784-791
Type of Manuscript:  PAPER
Category: Engineering Acoustics
Keyword: 
dodecahedral microphone arrayfrequency domain independent component analysiscomputational complexity reductionsignal to interference ratio improvement
 Summary | Full Text:PDF(2MB)

Acoustic Model Training Using Pseudo-Speaker Features Generated by MLLR Transformations for Robust Speaker-Independent Speech Recognition
Arata ITOH Sunao HARA Norihide KITAOKA Kazuya TAKEDA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/10/01
Vol. E95-D  No. 10  pp. 2479-2485
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech recognitionacoustic model trainingpseudo speakersfeature generationMLLR
 Summary | Full Text:PDF(724.6KB)

Blind Source Separation Using Dodecahedral Microphone Array under Reverberant Conditions
Motoki OGASAWARA Takanori NISHINO Kazuya TAKEDA 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2011/03/01
Vol. E94-A  No. 3  pp. 897-906
Type of Manuscript:  PAPER
Category: Engineering Acoustics
Keyword: 
dodecahedral microphone arrayfrequency domain independent component analysis (FD-ICA)signal-to-interference ratio improvement score
 Summary | Full Text:PDF(1.2MB)

Acoustic Feature Transformation Combining Average and Maximum Classification Error Minimization Criteria
Makoto SAKAI Norihide KITAOKA Kazuya TAKEDA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/07/01
Vol. E93-D  No. 7  pp. 2005-2008
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
speech recognitiondimensionality reductionBayes error
 Summary | Full Text:PDF(131.9KB)

Acoustic Feature Transformation Based on Discriminant Analysis Preserving Local Structure for Speech Recognition
Makoto SAKAI Norihide KITAOKA Kazuya TAKEDA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/05/01
Vol. E93-D  No. 5  pp. 1244-1252
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech recognitionfeature extractionmultidimensional signal processing
 Summary | Full Text:PDF(214.2KB)

Evaluation of Combinational Use of Discriminant Analysis-Based Acoustic Feature Transformation and Discriminative Training
Makoto SAKAI Norihide KITAOKA Yuya HATTORI Seiichi NAKAGAWA Kazuya TAKEDA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/02/01
Vol. E93-D  No. 2  pp. 395-398
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
speech recognitionfeature extractiondiscriminative training
 Summary | Full Text:PDF(78.2KB)

Selective Listening Point Audio Based on Blind Signal Separation and Stereophonic Technology
Kenta NIWA Takanori NISHINO Kazuya TAKEDA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2009/03/01
Vol. E92-D  No. 3  pp. 469-476
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
acoustic field representationblind source separationfrequency-domain independent component analysis (FD-ICA)spatial grouping
 Summary | Full Text:PDF(754.7KB)

Multichannel Speech Enhancement Based on Generalized Gamma Prior Distribution with Its Online Adaptive Estimation
Tran HUY DAT Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/03/01
Vol. E91-D  No. 3  pp. 439-447
Type of Manuscript:  Special Section PAPER (Special Section on Robust Speech Processing in Realistic Environments)
Category: Speech Enhancement
Keyword: 
multi-channel speech enhancementspeech recognitiongeneralized gamma distributionmoment matching
 Summary | Full Text:PDF(805.1KB)

FOREWORD
Kazuya TAKEDA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/03/01
Vol. E91-D  No. 3  pp. 391-392
Type of Manuscript:  FOREWORD
Category: 
Keyword: 
 Summary | Full Text:PDF(59.9KB)

CENSREC-3: An Evaluation Framework for Japanese Speech Recognition in Real Car-Driving Environments
Masakiyo FUJIMOTO Kazuya TAKEDA Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/11/01
Vol. E89-D  No. 11  pp. 2783-2793
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
noisy speech recognitioncommon evaluation frameworkin-car speech databaseCENSREC-3
 Summary | Full Text:PDF(1.1MB)

Gamma Modeling of Speech Power and Its On-Line Estimation for Statistical Speech Enhancement
Tran Huy DAT Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3  pp. 1040-1049
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Enhancement
Keyword: 
speech enhancementspeech recognitiongamma modelingfourth-order momentMMSEMAPspectral magnitudepowerlog-spectral magnitude
 Summary | Full Text:PDF(576.3KB)

Single-Channel Multiple Regression for In-Car Speech Enhancement
Weifeng LI Katsunobu ITOU Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3  pp. 1032-1039
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Enhancement
Keyword: 
speech enhancementspeech recognitionmulti-layer perceptronmean opinion scorepairwise preference testenvironmental adaptationK-means clustering
 Summary | Full Text:PDF(505.6KB)

Driver Identification Using Driving Behavior Signals
Toshihiro WAKITA Koji OZAWA Chiyomi MIYAJIMA Kei IGARASHI Katunobu ITOU Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3  pp. 1188-1194
Type of Manuscript:  PAPER
Category: Human-computer Interaction
Keyword: 
driving behaviorsignal processingpattern recognitionbiometrics
 Summary | Full Text:PDF(373.6KB)

Adaptive Nonlinear Regression Using Multiple Distributed Microphones for In-Car Speech Recognition
Weifeng LI Chiyomi MIYAJIMA Takanori NISHINO Katsunobu ITOU Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2005/07/01
Vol. E88-A  No. 7  pp. 1716-1723
Type of Manuscript:  Special Section PAPER (Special Section on Multi-channel Acoustic Signal Processing)
Category: Speech Enhancement
Keyword: 
speech recognitionsupport vector machinemulti-layer perceptronsignal-to-deviation ratioK-means clusteringadaptive beamforming
 Summary | Full Text:PDF(1MB)

Speech Recognition Using Finger Tapping Timings
Hiromitsu BAN Chiyomi MIYAJIMA Katsunobu ITOU Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 667-670
Type of Manuscript:  LETTER
Category: Speech and Hearing
Keyword: 
multi-modal speech recognitionhuman behavioral synchronization
 Summary | Full Text:PDF(514.6KB)

CIAIR In-Car Speech Corpus--Influence of Driving Status--
Nobuo KAWAGUCHI Shigeki MATSUBARA Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 578-582
Type of Manuscript:  Special Section LETTER (Special Section on Corpus-Based Speech Technologies)
Category: 
Keyword: 
speech corpusin-car speechITS
 Summary | Full Text:PDF(829.1KB)

Construction and Evaluation of a Large In-Car Speech Corpus
Kazuya TAKEDA Hiroshi FUJIMURA Katsunobu ITOU Nobuo KAWAGUCHI Shigeki MATSUBARA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 553-561
Type of Manuscript:  Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Speech Corpora and Related Topics
Keyword: 
speech corpusin-car speech recognitionperplexitySNR
 Summary | Full Text:PDF(1.2MB)

AURORA-2J: An Evaluation Framework for Japanese Noisy Speech Recognition
Satoshi NAKAMURA Kazuya TAKEDA Kazumasa YAMAMOTO Takeshi YAMADA Shingo KUROIWA Norihide KITAOKA Takanobu NISHIURA Akira SASOU Mitsunori MIZUMACHI Chiyomi MIYAJIMA Masakiyo FUJIMOTO Toshiki ENDO 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 535-544
Type of Manuscript:  Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Speech Corpora and Related Topics
Keyword: 
noisy speech recognitionevaluation platformperformance differences over speakersevaluation categories
 Summary | Full Text:PDF(1.7MB)

Multiple Regression of Log Spectra for In-Car Speech Recognition Using Multiple Distributed Microphones
Weifeng LI Tetsuya SHINDE Hiroshi FUJIMURA Chiyomi MIYAJIMA Takanori NISHINO Katunobu ITOU Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 384-390
Type of Manuscript:  Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Feature Extraction and Acoustic Medelings
Keyword: 
speech recognitionmicrophone arraysadaptive beamformingsignal-to-deviation ratiomultiple regression
 Summary | Full Text:PDF(568.7KB)

Direction of Arrival Estimation Using Nonlinear Microphone Array
Hidekazu KAMIYANAGIDA Hiroshi SARUWATARI Kazuya TAKEDA Fumitada ITAKURA Kiyohiro SHIKANO 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2001/04/01
Vol. E84-A  No. 4  pp. 999-1010
Type of Manuscript:  Special Section PAPER (Special Section on Acoustic Signal Processing)
Category: 
Keyword: 
nonlinear array signal processingmicrophone arrayDOA estimationcomplementary beamforming
 Summary | Full Text:PDF(977.5KB)

Speech Enhancement Using Nonlinear Microphone Array Based on Noise Adaptive Complementary Beamforming
Hiroshi SARUWATARI Shoji KAJITA Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2000/05/25
Vol. E83-A  No. 5  pp. 866-876
Type of Manuscript:  PAPER
Category: Engineering Acoustics
Keyword: 
speech enhancementmicrophone arraycomplementary beamformingnoise adaptationspectral subtraction
 Summary | Full Text:PDF(1.2MB)

Speech Enhancement Using Nonlinear Microphone Array Based on Complementary Beamforming
Hiroshi SARUWATARI Shoji KAJITA Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1999/08/25
Vol. E82-A  No. 8  pp. 1501-1510
Type of Manuscript:  Special Section PAPER (Special Section on Digital Signal Processing)
Category: 
Keyword: 
speech enhancementmicrophone arraycomplementary beamformingspectral subtractionspeech recognition
 Summary | Full Text:PDF(1MB)

Noise Robust Speech Recognition Using Subband-Crosscorrelation Analysis
Shoji KAJITA Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1998/10/25
Vol. E81-D  No. 10  pp. 1079-1086
Type of Manuscript:  PAPER
Category: Speech Processing and Acoustics
Keyword: 
subband processingautocorrelationcrosscorrelationnoise robustnessDTW word recognition
 Summary | Full Text:PDF(630.6KB)

An Acoustically Oriented Vocal-Tract Model
Hani C. YEHIA Kazuya TAKEDA Fumitada ITAKURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1996/08/25
Vol. E79-D  No. 8  pp. 1198-1208
Type of Manuscript:  PAPER
Category: Speech Processing and Acoustics
Keyword: 
vocal-tract log-area functionformant frequenciesfactor analysisindependent component analysissingular value decompositionarticulatory-to-acoustic inverse problem
 Summary | Full Text:PDF(978.6KB)

Error Analysis of Field Trial Results of a Spoken Dialogue System for Telecommunications Applications
Shingo KUROIWA Kazuya TAKEDA Masaki NAITO Naomi INOUE Seiichi YAMAMOTO 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/06/25
Vol. E78-D  No. 6  pp. 636-641
Type of Manuscript:  Special Section PAPER (Special Issue on Spoken Language Processing)
Category: 
Keyword: 
speech recognitiondialogue systemfield trialtelephone
 Summary | Full Text:PDF(589.1KB)