Keyword : acoustic model


Discriminative Learning of Filterbank Layer within Deep Neural Network Based Speech Recognition for Speaker Adaptation
Hiroshi SEKI Kazumasa YAMAMOTO Tomoyosi AKIBA Seiichi NAKAGAWA 
Publication:   
Publication Date: 2019/02/01
Vol. E102-D  No. 2 ; pp. 364-374
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech recognitiondeep neural networkacoustic modelspeaker adaptationfilterbank learning
 Summary | Full Text:PDF

DNN-Based Speech Synthesis Using Speaker Codes
Nobukatsu HOJO Yusuke IJIMA Hideyuki MIZUNO 
Publication:   
Publication Date: 2018/02/01
Vol. E101-D  No. 2 ; pp. 462-472
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech synthesisacoustic modeldeep neural networkspeaker codes
 Summary | Full Text:PDF

Combining Multiple Acoustic Models in GMM Spaces for Robust Speech Recognition
Byung Ok KANG Oh-Wook KWON 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/03/01
Vol. E99-D  No. 3 ; pp. 724-730
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
noise-robust speech recognitionacoustic modelGMM combinationnon-native speech recognition
 Summary | Full Text:PDF

Automatic Lecture Transcription Based on Discriminative Data Selection for Lightly Supervised Acoustic Model Training
Sheng LI Yuya AKITA Tatsuya KAWAHARA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2015/08/01
Vol. E98-D  No. 8 ; pp. 1545-1552
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
speech recognitionacoustic modellightly supervised traininglecture transcription
 Summary | Full Text:PDF

Learning Speech Variability in Discriminative Acoustic Model Adaptation
Shoei SATO Takahiro OKU Shinichi HOMMA Akio KOBAYASHI Toru IMAI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/09/01
Vol. E93-D  No. 9 ; pp. 2370-2378
Type of Manuscript:  Special Section PAPER (Special Section on Processing Natural Speech Variability for Improved Verbal Human-Computer Interaction)
Category: Adaptation
Keyword: 
speech recognitionspeech variabilitydiscriminative trainingacoustic model
 Summary | Full Text:PDF

Building an Effective Speech Corpus by Utilizing Statistical Multidimensional Scaling Method
Goshu NAGINO Makoto SHOZAKAI Tomoki TODA Hiroshi SARUWATARI Kiyohiro SHIKANO 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2008/03/01
Vol. E91-D  No. 3 ; pp. 607-614
Type of Manuscript:  Special Section PAPER (Special Section on Robust Speech Processing in Realistic Environments)
Category: Corpus
Keyword: 
speech corpuscost effectivespeaker selectionacoustic modelstatistical MDS method
 Summary | Full Text:PDF

Genetic Algorithm Based Optimization of Partly-Hidden Markov Model Structure Using Discriminative Criterion
Tetsuji OGAWA Tetsunori KOBAYASHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3 ; pp. 939-945
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Recognition
Keyword: 
acoustic modelhidden Markov modelpartly-hidden Markov modelweighted likelihood-ratio maximization criteriongenetic algorithmlecture talk speech recognition
 Summary | Full Text:PDF

Acoustic Model Adaptation Using First-Order Linear Prediction for Reverberant Speech
Tetsuya TAKIGUCHI Masafumi NISHIMURA Yasuo ARIKI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3 ; pp. 908-914
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Recognition
Keyword: 
acoustic modelreverberant speechadaptationhands-free speech recognition
 Summary | Full Text:PDF

Using Hybrid HMM/BN Acoustic Models: Design and Implementation Issues
Konstantin MARKOV Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3 ; pp. 981-988
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Recognition
Keyword: 
HMM/BNacoustic modelBayesian network
 Summary | Full Text:PDF

Automatic Generation of Non-uniform and Context-Dependent HMMs Based on the Variational Bayesian Approach
Takatoshi JITSUHIRO Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/03/01
Vol. E88-D  No. 3 ; pp. 391-400
Type of Manuscript:  Special Section PAPER (Special Section on Corpus-Based Speech Technologies)
Category: Feature Extraction and Acoustic Medelings
Keyword: 
speech recognitionacoustic modeltopology trainingSSS algorithmvariational Bayesian approach
 Summary | Full Text:PDF

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

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

Automatic Determination of the Number of Mixture Components for Continuous HMMs Based a Uniform Variance Criterion
Tetsuo KOSAKA Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/06/25
Vol. E78-D  No. 6 ; pp. 642-647
Type of Manuscript:  Special Section PAPER (Special Issue on Spoken Language Processing)
Category: 
Keyword: 
acoustic modelcontinuous mixture density HMMspeaker-independent speech recognitionmixture components
 Summary | Full Text:PDF