IEICE Trans

Sakriani SAKTI

Leveraging Neural Caption Translation with Visually Grounded Paraphrase Augmentation Johanes EFFENDI Sakriani SAKTI Katsuhito SUDOH Satoshi NAKAMURA
Publication: Publication Date: 2020/03/01 Vol. E103-D No. 3 pp. 674-683 Type of Manuscript: PAPER Category: Natural Language Processing Keyword: visually grounded paraphrase, data augmentation, neural machine translation,
	Summary \| Full Text:PDF

Recurrent Neural Network Compression Based on Low-Rank Tensor Representation Andros TJANDRA Sakriani SAKTI Satoshi NAKAMURA
Publication: Publication Date: 2020/02/01 Vol. E103-D No. 2 pp. 435-449 Type of Manuscript: PAPER Category: Music Information Processing Keyword: recurrent neural network, model compression, tensor decomposition, deep learning,
	Summary \| Full Text:PDF

Neural Oscillation-Based Classification of Japanese Spoken Sentences During Speech Perception Hiroki WATANABE Hiroki TANAKA Sakriani SAKTI Satoshi NAKAMURA
Publication: Publication Date: 2019/02/01 Vol. E102-D No. 2 pp. 383-391 Type of Manuscript: PAPER Category: Biocybernetics, Neurocomputing Keyword: brain-computer interface, electroencephalogram (EEG), neural decoding, neural oscillations, phase-locking,
	Summary \| Full Text:PDF

Construction of Spontaneous Emotion Corpus from Indonesian TV Talk Shows and Its Application on Multimodal Emotion Recognition Nurul LUBIS Dessi LESTARI Sakriani SAKTI Ayu PURWARIANTI Satoshi NAKAMURA
Publication: Publication Date: 2018/08/01 Vol. E101-D No. 8 pp. 2092-2100 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: Indonesian, audio-visual corpus, multimodal emotion recognition, spoken language processing,
	Summary \| Full Text:PDF

Learning Supervised Feature Transformations on Zero Resources for Improved Acoustic Unit Discovery Michael HECK Sakriani SAKTI Satoshi NAKAMURA
Publication: Publication Date: 2018/01/01 Vol. E101-D No. 1 pp. 205-214 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: acoustic unit discovery, Bayesian nonparametrics, feature transformation, unsupervised subword modeling, zero resource,
	Summary \| Full Text:PDF

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 synthesis, English-Read-by-Japanese, speaker individuality, HMM-based speech synthesis, prosody correction, phonetic correction,
	Summary \| Full Text:PDF

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 conversion, sample-based speech synthesis, speech parameter conversion, rich context model,
	Summary \| Full Text:PDF

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 system, dialog system, response retrieval, response generation, long short term memory neural network,
	Summary \| Full Text:PDF

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 model, independent component analysis (ICA), Wiener filter, noise removal, Wishart distribution, spatial correlation prior,
	Summary \| Full Text:PDF

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 training, multimodality, non-verbal behaviors, context information,
	Summary \| Full Text:PDF

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-aid, electrolaryngeal speech, spectral subtraction, voice conversion, hybrid approach,
	Summary \| Full Text:PDF

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 corpora, response generation, example-based dialog modeling, semantic similarity, cosine similarity, machine translation,
	Summary \| Full Text:PDF

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 voice, voice conversion, perceived age, spectral and prosodic features, subjective evaluations,
	Summary \| Full Text:PDF

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 selection, linear regression, MLLR, fMLLR, model space adaptation, feature space adaptation,
	Summary \| Full Text:PDF

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 conversion, out-of-vocabulary word, online discriminative training, structured learning, AROW,
	Summary \| Full Text:PDF

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 speech, noisy channel approach, joint-sequence models, statistical machine translation,
	Summary \| Full Text:PDF

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 model, pentaphone, HMM/BN acoustic model,
	Summary \| Full Text:PDF

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 framework, wide phonetic context model, acoustic rescoring,
	Summary \| Full Text:PDF