Sakriani SAKTI


Non-Native Text-to-Speech Preserving Speaker Individuality Based on Partial Correction of Prosodic and Phonetic Characteristics
Yuji OSHIMA Shinnosuke TAKAMICHI Tomoki TODA Graham NEUBIG Sakriani SAKTI Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/12/01
Vol. E99-D  No. 12  pp. 3132-3139
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
cross-lingual speech synthesisEnglish-Read-by-Japanesespeaker individualityHMM-based speech synthesisprosody correctionphonetic correction
 Summary | Full Text:PDF(1.2MB)

A Statistical Sample-Based Approach to GMM-Based Voice Conversion Using Tied-Covariance Acoustic Models
Shinnosuke TAKAMICHI Tomoki TODA Graham NEUBIG Sakriani SAKTI Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2490-2498
Type of Manuscript:  Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Voice conversion
Keyword: 
GMM-based voice conversionsample-based speech synthesisspeech parameter conversionrich context model
 Summary | Full Text:PDF(846.3KB)

Neural Network Approaches to Dialog Response Retrieval and Generation
Lasguido NIO Sakriani SAKTI Graham NEUBIG Koichiro YOSHINO Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2508-2517
Type of Manuscript:  Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Spoken dialog system
Keyword: 
example-based dialog systemdialog systemresponse retrievalresponse generationlong short term memory neural network
 Summary | Full Text:PDF(1.5MB)

Enhancing Event-Related Potentials Based on Maximum a Posteriori Estimation with a Spatial Correlation Prior
Hayato MAKI Tomoki TODA Sakriani SAKTI Graham NEUBIG Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/06/01
Vol. E99-D  No. 6  pp. 1437-1446
Type of Manuscript:  Special Section PAPER (Special Section on Human Cognition and Behavioral Science and Technology)
Category: 
Keyword: 
electroencephalogram (EEG)event-related potential (ERP)generative modelindependent component analysis (ICA)Wiener filternoise removalWishart distributionspatial correlation prior
 Summary | Full Text:PDF(1MB)

NOCOA+: Multimodal Computer-Based Training for Social and Communication Skills
Hiroki TANAKA Sakriani SAKTI Graham NEUBIG Tomoki TODA Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2015/08/01
Vol. E98-D  No. 8  pp. 1536-1544
Type of Manuscript:  PAPER
Category: Educational Technology
Keyword: 
computer-based trainingmultimodalitynon-verbal behaviorscontext information
 Summary | Full Text:PDF(726.4KB)

Variable Selection Linear Regression for Robust Speech Recognition
Yu TSAO Ting-Yao HU Sakriani SAKTI Satoshi NAKAMURA Lin-shan LEE 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/06/01
Vol. E97-D  No. 6  pp. 1477-1487
Type of Manuscript:  Special Section PAPER (Special Section on Advances in Modeling for Real-world Speech Information Processing and its Application)
Category: Speech Recognition
Keyword: 
variable selectionlinear regressionMLLRfMLLRmodel space adaptationfeature space adaptation
 Summary | Full Text:PDF(1MB)

Voice Timbre Control Based on Perceived Age in Singing Voice Conversion
Kazuhiro KOBAYASHI Tomoki TODA Hironori DOI Tomoyasu NAKANO Masataka GOTO Graham NEUBIG Sakriani SAKTI Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/06/01
Vol. E97-D  No. 6  pp. 1419-1428
Type of Manuscript:  Special Section PAPER (Special Section on Advances in Modeling for Real-world Speech Information Processing and its Application)
Category: Voice Conversion and Speech Enhancement
Keyword: 
singing voicevoice conversionperceived agespectral and prosodic featuressubjective evaluations
 Summary | Full Text:PDF(1MB)

A Hybrid Approach to Electrolaryngeal Speech Enhancement Based on Noise Reduction and Statistical Excitation Generation
Kou TANAKA Tomoki TODA Graham NEUBIG Sakriani SAKTI Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/06/01
Vol. E97-D  No. 6  pp. 1429-1437
Type of Manuscript:  Special Section PAPER (Special Section on Advances in Modeling for Real-world Speech Information Processing and its Application)
Category: Voice Conversion and Speech Enhancement
Keyword: 
speaking-aidelectrolaryngeal speechspectral subtractionvoice conversionhybrid approach
 Summary | Full Text:PDF(1.3MB)

Structured Adaptive Regularization of Weight Vectors for a Robust Grapheme-to-Phoneme Conversion Model
Keigo KUBO Sakriani SAKTI Graham NEUBIG Tomoki TODA Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/06/01
Vol. E97-D  No. 6  pp. 1468-1476
Type of Manuscript:  Special Section PAPER (Special Section on Advances in Modeling for Real-world Speech Information Processing and its Application)
Category: Speech Synthesis and Related Topics
Keyword: 
g2p conversionout-of-vocabulary wordonline discriminative trainingstructured learningAROW
 Summary | Full Text:PDF(420.4KB)

Utilizing Human-to-Human Conversation Examples for a Multi Domain Chat-Oriented Dialog System
Lasguido NIO Sakriani SAKTI Graham NEUBIG Tomoki TODA Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2014/06/01
Vol. E97-D  No. 6  pp. 1497-1505
Type of Manuscript:  Special Section PAPER (Special Section on Advances in Modeling for Real-world Speech Information Processing and its Application)
Category: Dialog System
Keyword: 
dialog corporaresponse generationexample-based dialog modelingsemantic similaritycosine similaritymachine translation
 Summary | Full Text:PDF(806.8KB)

Sequence-Based Pronunciation Variation Modeling for Spontaneous ASR Using a Noisy Channel Approach
Hansjorg HOFMANN Sakriani SAKTI Chiori HORI Hideki KASHIOKA Satoshi NAKAMURA Wolfgang MINKER 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2012/08/01
Vol. E95-D  No. 8  pp. 2084-2093
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
spontaneous speechnoisy channel approachjoint-sequence modelsstatistical machine translation
 Summary | Full Text:PDF(1.1MB)

Improving Acoustic Model Precision by Incorporating a Wide Phonetic Context Based on a Bayesian Framework
Sakriani SAKTI Satoshi NAKAMURA Konstantin MARKOV 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3  pp. 946-953
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Recognition
Keyword: 
Bayesian frameworkwide phonetic context modelacoustic rescoring
 Summary | Full Text:PDF(355.8KB)

A Hybrid HMM/BN Acoustic Model Utilizing Pentaphone-Context Dependency
Sakriani SAKTI Konstantin MARKOV Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3  pp. 954-961
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Recognition
Keyword: 
wide phonetic context modelpentaphoneHMM/BN acoustic model
 Summary | Full Text:PDF(448.2KB)