Seiichi NAKAGAWA


Risk-Based Semi-Supervised Discriminative Language Modeling for Broadcast Transcription
Akio KOBAYASHI Takahiro OKU Toru IMAI Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/11/01
Vol. E95-D  No. 11  pp. 2674-2681
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
discriminative trainingsemi-supervised traininglanguage modelingBayes risk minimization
 Summary | Full Text:PDF(263.5KB)

Class-Based N-Gram Language Model for New Words Using Out-of-Vocabulary to In-Vocabulary Similarity
Welly NAPTALI Masatoshi TSUCHIYA Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/09/01
Vol. E95-D  No. 9  pp. 2308-2317
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
out-of-vocabularyclass-based n-gramlanguage modeladjusted perplexityspeech recognition
 Summary | Full Text:PDF(365.4KB)

Hidden Conditional Neural Fields for Continuous Phoneme Speech Recognition
Yasuhisa FUJII Kazumasa YAMAMOTO Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/08/01
Vol. E95-D  No. 8  pp. 2094-2104
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
hidden conditional neural fieldshidden conditional random fieldshidden Markov modelspeech recognitiondeep learning
 Summary | Full Text:PDF(324.9KB)

Improving the Readability of ASR Results for Lectures Using Multiple Hypotheses and Sentence-Level Knowledge
Yasuhisa FUJII Kazumasa YAMAMOTO Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/04/01
Vol. E95-D  No. 4  pp. 1101-1111
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
improving readability of ASR resultsconfusion networkautomatic speech recognitionclassroom lecture speechsentence-level knowledge
 Summary | Full Text:PDF(798.1KB)

Distant-Talking Speech Recognition Based on Spectral Subtraction by Multi-Channel LMS Algorithm
Longbiao WANG Norihide KITAOKA Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2011/03/01
Vol. E94-D  No. 3  pp. 659-667
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
distant-talking speech recognitionblind dereverberationmulti-channel least mean squaresspectral subtractioncepstral mean normalization
 Summary | Full Text:PDF(321.4KB)

Speaker Recognition by Combining MFCC and Phase Information in Noisy Conditions
Longbiao WANG Kazue MINAMI Kazumasa YAMAMOTO Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/09/01
Vol. E93-D  No. 9  pp. 2397-2406
Type of Manuscript:  Special Section PAPER (Special Section on Processing Natural Speech Variability for Improved Verbal Human-Computer Interaction)
Category: Speaker Recognition
Keyword: 
speaker identificationphase informationMFCCnoisy environmentGMM
 Summary | Full Text:PDF(856.9KB)

Distant Speech Recognition Using a Microphone Array Network
Alberto Yoshihiro NAKANO Seiichi NAKAGAWA Kazumasa YAMAMOTO 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/09/01
Vol. E93-D  No. 9  pp. 2451-2462
Type of Manuscript:  Special Section PAPER (Special Section on Processing Natural Speech Variability for Improved Verbal Human-Computer Interaction)
Category: Microphone Array
Keyword: 
distant speech recognitionmicrophone array networkGMM-based CMNspeaker's position and orientation estimation
 Summary | Full Text:PDF(449.7KB)

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)

Noisy Speech Recognition Based on Integration/Selection of Multiple Noise Suppression Methods Using Noise GMMs
Norihide KITAOKA Souta HAMAGUCHI Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/03/01
Vol. E91-D  No. 3  pp. 411-421
Type of Manuscript:  Special Section PAPER (Special Section on Robust Speech Processing in Realistic Environments)
Category: Noisy Speech Recognition
Keyword: 
noisy speech recognitionnoise suppression method selectionCENSREC-1
 Summary | Full Text:PDF(879.8KB)

Robust Speech Recognition by Combining Short-Term and Long-Term Spectrum Based Position-Dependent CMN with Conventional CMN
Longbiao WANG Seiichi NAKAGAWA Norihide KITAOKA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/03/01
Vol. E91-D  No. 3  pp. 457-466
Type of Manuscript:  Special Section PAPER (Special Section on Robust Speech Processing in Realistic Environments)
Category: ASR under Reverberant Conditions
Keyword: 
robust speech recognitiondistant-talking environmentCMNlong-term spectrum
 Summary | Full Text:PDF(343.3KB)

Linear Discriminant Analysis Using a Generalized Mean of Class Covariances and Its Application to Speech Recognition
Makoto SAKAI Norihide KITAOKA Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/03/01
Vol. E91-D  No. 3  pp. 478-487
Type of Manuscript:  Special Section PAPER (Special Section on Robust Speech Processing in Realistic Environments)
Category: Feature Extraction
Keyword: 
speech recognitionfeature extractionmultidimensional signal processing
 Summary | Full Text:PDF(421.5KB)

A Machine Learning Approach for an Indonesian-English Cross Language Question Answering System
Ayu PURWARIANTI Masatoshi TSUCHIYA Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2007/11/01
Vol. E90-D  No. 11  pp. 1841-1852
Type of Manuscript:  PAPER
Category: Natural Language Processing
Keyword: 
Cross Language Question AnsweringIndonesian-English CLQAlimited resource languagemachine learning
 Summary | Full Text:PDF(523KB)

Text-Independent/Text-Prompted Speaker Recognition by Combining Speaker-Specific GMM with Speaker Adapted Syllable-Based HMM
Seiichi NAKAGAWA Wei ZHANG Mitsuo TAKAHASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3  pp. 1058-1065
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speaker Recognition
Keyword: 
speaker identificationGMMHMMtext verification
 Summary | Full Text:PDF(1022.4KB)

Improving Keyword Recognition of Spoken Queries by Combining Multiple Speech Recognizer's Outputs for Speech-driven WEB Retrieval Task
Masahiko MATSUSHITA Hiromitsu NISHIZAKI Takehito UTSURO Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 472-480
Type of Manuscript:  Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Spoken Language Systems
Keyword: 
speech recognitionmachine learningmultiple LVCSR modelsWEB retrieval
 Summary | Full Text:PDF(1.7MB)

An Unsupervised Speaker Adaptation Method for Lecture-Style Spontaneous Speech Recognition Using Multiple Recognition Systems
Seiichi NAKAGAWA Tomohiro WATANABE Hiromitsu NISHIZAKI Takehito UTSURO 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3  pp. 463-471
Type of Manuscript:  Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Spoken Language Systems
Keyword: 
spontaneous speech recognitionunsupervised speaker adaptationconfidence measuremultiple LVCSR models
 Summary | Full Text:PDF(641KB)

A Statistical Method of Evaluating Pronunciation Proficiency for English Words Spoken by Japanese
Seiichi NAKAGAWA Naoki NAKAMURA Kazumasa MORI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2004/07/01
Vol. E87-D  No. 7  pp. 1917-1922
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
CALLevaluation of pronunciation proficiencyEnglish learningspeech recognition
 Summary | Full Text:PDF(463.1KB)

Continuous Speech Recognition Using an On-Line Speaker Adaptation Method Based on Automatic Speaker Clustering
Wei ZHANG Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2003/03/01
Vol. E86-D  No. 3  pp. 464-473
Type of Manuscript:  Special Section PAPER (Special Issue on Speech Information Processing)
Category: Speech and Speaker Recognition
Keyword: 
speaker adaptationspeech recognitionspeaker clusteringMLLRMAP
 Summary | Full Text:PDF(910.3KB)

A Survey on Automatic Speech Recognition
Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2002/03/01
Vol. E85-D  No. 3  pp. 465-486
Type of Manuscript:  INVITED SURVEY PAPER
Category: Speech and Hearing
Keyword: 
speech recognitionacoustic modelHMMlanguage modelngram
 Summary | Full Text:PDF(1.1MB)

Text-Independent Speaker Identification Utilizing Likelihood Normalization Technique
Konstantin P. MARKOV Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1997/05/25
Vol. E80-D  No. 5  pp. 585-593
Type of Manuscript:  PAPER
Category: Speech Processing and Acoustics
Keyword: 
speaker identificationlikelihood normalizationframe level processing
 Summary | Full Text:PDF(713.1KB)

Succeeding Word Prediction for Speech Recognition Based on Stochastic Language Model
Min ZHOU Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1996/04/25
Vol. E79-D  No. 4  pp. 333-342
Type of Manuscript:  PAPER
Category: Speech Processing and Acoustics
Keyword: 
stochastic language modelbigramtrigramHMMbigram-HMMcontext-free grammarentropyperplexityprediction rate
 Summary | Full Text:PDF(783.5KB)

A Comparative Study of Output Probability Functions in HMMs
Seiichi NAKAGAWA Li ZHAO Hideyuki SUZUKI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/06/25
Vol. E78-D  No. 6  pp. 669-675
Type of Manuscript:  Special Section PAPER (Special Issue on Spoken Language Processing)
Category: 
Keyword: 
HMMRBF-based HMMVQ-distortion based HMMoutput probability functionspeaker-independentspoken digit recognition
 Summary | Full Text:PDF(613.8KB)

Relationship among Recognition Rate, Rejection Rate and False Alarm Rate in a Spoken Word Recognition System
Atsuhiko KAI Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/06/25
Vol. E78-D  No. 6  pp. 698-704
Type of Manuscript:  Special Section PAPER (Special Issue on Spoken Language Processing)
Category: 
Keyword: 
speech recognitionunknown word processingsimulationrejection rate
 Summary | Full Text:PDF(537.8KB)

A Spoken Dialog System with Verification and Clarification Queries
Mikio YAMAMOTO Satoshi KOBAYASHI Yuji MORIYA Seiichi NAKAGAWA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1993/01/25
Vol. E76-D  No. 1  pp. 84-94
Type of Manuscript:  Special Section PAPER (Special Issue on Speech and Discourse Processing in Dialogue Systems)
Category: 
Keyword: 
natural language processingspeech recognitiondialog systemverificationclarification
 Summary | Full Text:PDF(938KB)

Comparison of Language Models by Context-Free Grammar, Bigram and Quasi/Simplified-Trigram
Seiichi NAKAGAWA Isao MURASE 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1991/07/25
Vol. E74-A  No. 7  pp. 1897-1905
Type of Manuscript:  Special Section PAPER (Special Issue on Continuous Speech Recognition and Understanding)
Category: Language Modeling
Keyword: 
 Summary | Full Text:PDF(606.7KB)

Comparison of Syntax-0riented Spoken Japanese Understanding System with Semantic-Oriented System
Seiichi NAKAGAWA Yoshimitsu HIRATA Isao MURASE Tomohiro TANOUE 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1991/07/25
Vol. E74-A  No. 7  pp. 1854-1862
Type of Manuscript:  Special Section PAPER (Special Issue on Continuous Speech Recognition and Understanding)
Category: Speech Understanding
Keyword: 
 Summary | Full Text:PDF(747.9KB)