Tasuku Oonishi

According to our database, Tasuku Oonishi authored at least 9 papers between 2007 and 2013.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2013

A noise-robust speech recognition approach incorporating normalized speech/non-speech likelihood into hypothesis scores.

Tasuku Oonishi, Koji Iwano, Sadaoki Furui

Speech Commun., 2013

2010

VAD-measure-embedded decoder with online model adaptation.

Tasuku Oonishi, Koji Iwano, Sadaoki Furui

Proceedings of the INTERSPEECH 2010, 2010

2009

Harnessing graphics processors for the fast computation of acoustic likelihoods in speech recognition.

Paul R. Dixon, Tasuku Oonishi, Sadaoki Furui

Comput. Speech Lang., 2009

Robust speech recognition using VAD-measure-embedded decoder.

Tasuku Oonishi, Paul R. Dixon, Koji Iwano, Sadaoki Furui

Proceedings of the INTERSPEECH 2009, 2009

Generalization of specialized on-the-fly composition.

Tasuku Oonishi, Paul R. Dixon, Koji Iwano, Sadaoki Furui

Proceedings of the IEEE International Conference on Acoustics, 2009

Fast acoustic computations using graphics processors.

Paul R. Dixon, Tasuku Oonishi, Sadaoki Furui

Proceedings of the IEEE International Conference on Acoustics, 2009

Combining a Two-step Conditional Random Field Model and a Joint Source Channel Model for Machine Transliteration.

Dong Yang, Paul R. Dixon, Yi-Cheng Pan, Tasuku Oonishi, Masanobu Nakamura, Sadaoki Furui

Proceedings of the 2009 Named Entities Workshop: Shared Task on Transliteration, 2009

2008

Implementation and evaluation of fast on-the-fly WFST composition algorithms.

Tasuku Oonishi, Paul R. Dixon, Koji Iwano, Sadaoki Furui

Proceedings of the INTERSPEECH 2008, 2008

2007

The Titech large vocabulary WFST speech recognition system.

Paul R. Dixon, Diamantino Caseiro, Tasuku Oonishi, Sadaoki Furui

Proceedings of the IEEE Workshop on Automatic Speech Recognition & Understanding, 2007