Yuuki Tachioka

发表

Multi-channel Non-negative Matrix Factorization Initialized with Full-rank and Rank-1 Spatial Correlation Matrix for Speech Recognition

Yuuki Tachioka, 2018, 2018 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS).

Coupled Initialization of Multi-Channel Non-Negative Matrix Factorization Based on Spatial and Spectral Information

Yuuki Tachioka, Shingo Uenohara, Jonathan Le Roux, 2017, INTERSPEECH.

Knowledge Distillation Using Soft and Hard Labels and Annealing for Acoustic Model Training

Yuuki Tachioka, 2019, 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE).

Advanced ASR Technologies for Mitsubishi Electric Speech Applications

Yuuki Tachioka, Tomohiro Narita, Jun Ishii, 2017, New Era for Robust Speech Recognition, Exploiting Deep Learning.

Direction of arrival estimation by cross-power spectrum phase analysis using prior distributions and voice activity detection information

Yuuki Tachioka, Tomohiro Narita, Tomohiro Iwasaki, 2012 .

Voice Activity Detection Using Density Ratio Esrimation of Speech and Noise

Yuuki Tachioka, Tomohiro Narita, Jun Ishii, 2013 .

Sequence discriminative training for low-rank deep neural networks

Yuuki Tachioka, Jonathan Le Roux, John R. Hershey, 2014, 2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

Activation Driven Synchronized Joint Diagonalization for Underdetermined Sound Source Separation

Yuuki Tachioka, Taiki Izumi, Shingo Uenohara, 2019, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Discriminative method for recurrent neural network language models

Yuuki Tachioka, Shinji Watanabe, Shinji Watanabe, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Feature-space structural MAPLR with regression tree-based multiple transformation matrices for DNN

Yuuki Tachioka, Shinji Watanabe, Jun Ishii, 2015, 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

Ensemble integration of calibrated speaker localization and statistical speech detection in domestic environments

Yuuki Tachioka, Jonathan Le Roux, Shinji Watanabe, 2014, 2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA).

Effectiveness of dereverberation, feature transformation, discriminative training methods, and system combination approach for various reverberant environments

Yuuki Tachioka, Shinji Watanabe, Tomohiro Narita, 2015, EURASIP J. Adv. Signal Process..

Optimal design of a sound reflector by particle swarm optimization

Yuuki Tachioka, 2013 .

Voice activity detection based on density ratio estimation and system combination

Yuuki Tachioka, Tomohiro Narita, Jun Ishii, 2013, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.

Long short-term memory recurrent-neural-network-based bandwidth extension for automatic speech recognition

Yuuki Tachioka, Jun Ishii, Yuuki Tachioka, 2016 .

Prior-based Binary Masking and Discriminative Methods for Reverberant and Noisy Speech Recognition Using Distant Stereo Microphones

Yuuki Tachioka, Jonathan Le Roux, John R. Hershey, 2017, J. Inf. Process..

Template-Based Method for Compensation of Time Difference of Arrival in Passive Sound Source Localization under Reverberant and Noisy Environments

Yuuki Tachioka, Tomohiro Narita, Yuuki Tachioka, 2017 .

Dereverberation method with reverberation time estimation using floored ratio of spectral subtraction

Yuuki Tachioka, Toshiyuki Hanazawa, Tomohiro Iwasaki, 2013 .

Optimal automatic speech recognition system selection for noisy environments

Yuuki Tachioka, Tomohiro Narita, 2016, 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA).

Sequential maximum mutual information linear discriminant analysis for speech recognition

Yuuki Tachioka, Jonathan Le Roux, John R. Hershey, 2014, INTERSPEECH.

Objective Measurement of the Relationship between Variants in Classical Literature

Yuuki Tachioka, 2013, 2013 International Conference on Culture and Computing.

Automatic Determination of the Optimum Number of Updates in Synchronized Joint Diagonalization

Yuuki Tachioka, Shingo Uenohara, Ken'ichi Furuya, 2019, CISIS.

Multilingual acoustic model training based on phoneme set conversion

Yuuki Tachioka, 2020, 2020 IEEE 9th Global Conference on Consumer Electronics (GCCE).

Uncertainty training and decoding methods of deep neural networks based on stochastic representation of enhanced features

Yuuki Tachioka, Shinji Watanabe, 2015, INTERSPEECH.

Analysis of Initial-value Dependency in Multichannel Nonnegative Matrix Factorization for Blind Source Separation and Speech Recognition

Yuuki Tachioka, Shingo Uenohara, Tomohiro Narita, 2017 .

Hypothesis Correction Based on Semi-character Recurrent Neural Network for End-to-end Speech Recognition

Yuuki Tachioka, Yuuki Tachioka, 2019, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Permutation Alignment Based on MUSIC Spectrum Discrepancy for Blind Source Separation

Yuuki Tachioka, 2019, 2019 27th European Signal Processing Conference (EUSIPCO).

DISCRIMINATIVE METHODS FOR NOISE ROBUST SPEECH RECOGNITION: A CHIME CHALLENGE BENCHMARK

Yuuki Tachioka, Jonathan Le Roux, John R. Hershey, 2013 .

Deep recurrent de-noising auto-encoder and blind de-reverberation for reverberated speech recognition

Yuuki Tachioka, Björn W. Schuller, Shinji Watanabe, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Effectiveness of discriminative training and feature transformation for reverberated and noisy speech

Yuuki Tachioka, John R. Hershey, Shinji Watanabe, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Semi‐blind source separation using binary masking and independent vector analysis

Yuuki Tachioka, Tomohiro Narita, Jun Ishii, 2015 .

Elimination of Artifacts on Aperture Synthesis Images Using Ultrasonic Sensor's Directivity and the Ratio of Intensity

Yuuki Tachioka, Jun Ishii, Takashi Hirano, 2013 .

Speech recognition performance estimation for clipped speech based on objective measures

Yuuki Tachioka, Tomohiro Narita, Jun Ishii, 2014 .

Multi-channel non-negative matrix factorization with binary mask initialization for automatic speech recognition

Yuuki Tachioka, Shingo Uenohara, Tomohiro Narita, 2016 .

Discriminative training of acoustic models for system combination

Yuuki Tachioka, Shinji Watanabe, 2013, INTERSPEECH.

A generalized discriminative training framework for system combination

Yuuki Tachioka, Jonathan Le Roux, John R. Hershey, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Dnn-Based Voice Activity Detection Using Auxiliary Speech Models in Noisy Environments

Yuuki Tachioka, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The MERL/MELCO/TUM system for the REVERB Challenge using Deep Recurrent Neural Network Feature Enhancement

Yuuki Tachioka, Jonathan Le Roux, John R. Hershey, 2014, ICASSP 2014.

Sequential initialization of multichannel nonnegative matrix factorization for sound source separation

Yuuki Tachioka, Shingo Uenohara, Tomohiro Narita, 2017, 2017 IEEE 6th Global Conference on Consumer Electronics (GCCE).