IEICE Trans

Sumitaka SAKAUCHI

Latent Words Recurrent Neural Network Language Models for Automatic Speech Recognition Ryo MASUMURA Taichi ASAMI Takanobu OBA Sumitaka SAKAUCHI Akinori ITO
Publication: Publication Date: 2019/12/01 Vol. E102-D No. 12 pp. 2557-2567 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: latent words recurrent neural network language models, n-gram approximation, Viterbi approximation, automatic speech recognition,
	Summary \| Full Text:PDF(732.2KB)

Domain Adaptation Based on Mixture of Latent Words Language Models for Automatic Speech Recognition Ryo MASUMURA Taichi ASAMI Takanobu OBA Hirokazu MASATAKI Sumitaka SAKAUCHI Akinori ITO
Publication: Publication Date: 2018/06/01 Vol. E101-D No. 6 pp. 1581-1590 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: domain adaptation, mixture modeling, latent words language models, latent variable space, automatic speech recognition,
	Summary \| Full Text:PDF(792.7KB)

Investigation of Combining Various Major Language Model Technologies including Data Expansion and Adaptation Ryo MASUMURA Taichi ASAMI Takanobu OBA Hirokazu MASATAKI Sumitaka SAKAUCHI Akinori ITO
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2016/10/01 Vol. E99-D No. 10 pp. 2452-2461 Type of Manuscript: Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing) Category: Language modeling Keyword: language models, direct decoding, unsupervised adaptation, rescoring, spontaneous speech recognition,
	Summary \| Full Text:PDF(333.7KB)

N-gram Approximation of Latent Words Language Models for Domain Robust Automatic Speech Recognition Ryo MASUMURA Taichi ASAMI Takanobu OBA Hirokazu MASATAKI Sumitaka SAKAUCHI Satoshi TAKAHASHI
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2016/10/01 Vol. E99-D No. 10 pp. 2462-2470 Type of Manuscript: Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing) Category: Language modeling Keyword: language models, domain robustness, latent words language models, n-gram approximation, automatic speech recognition,
	Summary \| Full Text:PDF(539.2KB)

An Estimation Method of Sound Source Orientation Using Eigenspace Variation of Spatial Correlation Matrix Kenta NIWA Yusuke HIOKA Sumitaka SAKAUCHI Ken'ichi FURUYA Yoichi HANEDA
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 2013/09/01 Vol. E96-A No. 9 pp. 1831-1839 Type of Manuscript: PAPER Category: Engineering Acoustics Keyword: Microphone array, sound source orientation, reflected sound, transfer function, spatial correlation matrix,
	Summary \| Full Text:PDF(2MB)

Subjective Assessment of the Desired Echo Return Loss for Subband Acoustic Echo Cancellers Sumitaka SAKAUCHI Yoichi HANEDA Shoji MAKINO Masashi TANAKA Yutaka KANEDA
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 2000/12/25 Vol. E83-A No. 12 pp. 2633-2639 Type of Manuscript: PAPER Category: Engineering Acoustics Keyword: hands-free telecommunication, subband echo canceller, transmission delay, reverberation, auditory characteristics,
	Summary \| Full Text:PDF(1.3MB)