Yuuki Tachioka
Yuuki Tachioka
Denso IT Laboratory
Bestätigte E-Mail-Adresse bei d-itlab.co.jp - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition
F Weninger, S Watanabe, Y Tachioka, B Schuller
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
792014
Discriminative methods for noise robust speech recognition: A CHiME challenge benchmark
Y Tachioka, S Watanabe, J Le Roux, JR Hershey
The 2nd International Workshop on Machine Listening in Multisource …, 2013
582013
THE MERL/MELCO/TUM SYSTEM FOR THE REVERB CHALLENGE USING DEEP RECURRENT NEURAL NETWORK FEATURE ENHANCEMENT
F Weninger, S Watanabe, J Le Roux, JR Hershey, Y Tachioka, J Geiger, ...
REVERB workshop 1 (1), ID 1569884459 pp.1-8, 2014
392014
Effectiveness of discriminative training and feature transformation for reverberated and noisy speech
Y Tachioka, S Watanabe, JR Hershey
2013 IEEE International Conference on Acoustics, Speech and Signal …, 2013
282013
DUAL SYSTEM COMBINATION APPROACH FOR VARIOUS REVERBERANT ENVIRONMENTS WITH DEREVERBERATION TECHNIQUES
Y Tachioka, T Narita, F Weninger, S Watanabe
REVERB workshop, ID 1569886337 pp.1-8, 2014
212014
Discriminative method for recurrent neural network language models
Y Tachioka, S Watanabe
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
172015
Speech recognition performance estimation for clipped speech based on objective measures
Y Tachioka, T Narita, J Ishii
Acoustical Science and Technology 35 (6), 324-326, 2014
142014
Uncertainty training and decoding methods of deep neural networks based on stochastic representation of enhanced features
Y Tachioka, S Watanabe
Sixteenth Annual Conference of the International Speech Communication …, 2015
132015
Direction of arrival estimation by cross-power spectrum phase analysis using prior distributions and voice activity detection information
Y Tachioka, T Narita, T Iwasaki
Acoustical Science and Technology 33 (1), 68-71, 2012
132012
Application of the constrained interpolation profile method to room acoustic problems: Examination of boundary modeling and spatial/time discretization
Y Tachioka, Y Yasuda, T Sakuma
Acoustical Science and Technology 33 (1), 21-32, 2012
122012
A generalized discriminative training framework for system combination
Y Tachioka, S Watanabe, J Le Roux, JR Hershey
2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 43-48, 2013
102013
Coupled Initialization of Multi-Channel Non-Negative Matrix Factorization Based on Spatial and Spectral Information.
Y Tachioka, T Narita, I Miura, T Uramoto, N Monta, S Uenohara, ...
INTERSPEECH, 2461-2465, 2017
82017
Analysis of initial-value dependency in multichannel nonnegative matrix factorization for blind source separation and speech recognition
I Miura, Y Tachioka, T Narita, J Ishii, F Yoshiyama, S Uenohara, K Furuya
IEICE Transactions on Information and Systems 100 (3), 376-384, 2017
82017
Dereverberation method with reverberation time estimation using floored ratio of spectral subtraction
Y Tachioka, T Hanazawa, T Iwasaki
Acoustical Science and Technology 34 (3), 212-215, 2013
82013
Discriminative training of acoustic models for system combination.
Y Tachioka, S Watanabe
INTERSPEECH, 2355-2359, 2013
82013
Feature-space structural MAPLR with regression tree-based multiple transformation matrices for DNN
H Kanagawa, Y Tachioka, S Watanabe, J Ishii
2015 Asia-Pacific Signal and Information Processing Association Annual …, 2015
72015
DNN-based voice activity detection using auxiliary speech models in noisy environments
Y Tachioka
2018 IEEE International Conference on Acoustics, Speech and Signal …, 2018
62018
Ensemble integration of calibrated speaker localization and statistical speech detection in domestic environments
Y Tachioka, T Narita, S Watanabe, J Le Roux
2014 4th Joint Workshop on Hands-free Speech Communication and Microphone …, 2014
62014
Sequential initialization of multichannel nonnegative matrix factorization for sound source separation
T Uramoto, Y Tachioka, T Narita, I Miura, S Uenohara, K Furuya
2017 IEEE 6th Global Conference on Consumer Electronics (GCCE), 1-2, 2017
42017
Long short-term memory recurrent-neural-network-based bandwidth extension for automatic speech recognition
Y Tachioka, J Ishii
Acoustical Science and Technology 37 (6), 319-321, 2016
42016
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20