Tatsuya Kawahara

Publications
Influence

Julius - an open source real-time large vocabulary recognition engine

A. Lee, Tatsuya Kawahara, K. Shikano
Computer Science
INTERSPEECH
1 September 2001

EUROSPEECH2001: the 7th European Conference on Speech Communication and Technology, September 3-7, 2001, Aalborg, Denmark. Expand

Recent Development of Open-Source Speech Recognition Engine Julius

A. Lee, Tatsuya Kawahara
Computer Science
4 October 2009

Julius is an open-source large-vocabulary speech recognition software used for both academic research and industrial applications. Expand

Overview of the IR for Spoken Documents Task in NTCIR-9 Workshop

T. Akiba, H. Nishizaki, K. Aikawa, Tatsuya Kawahara, T. Matsui
Computer Science
NTCIR
2011

This paper describes an overview of the IR for Spoken Documents Task in NTCIR-9 Workshop. Expand

Benchmark test for speech recognition using the Corpus of Spontaneous Japanese

Tatsuya Kawahara
Computer Science
2003

We present benchmark results of automatic speech recognition using the Corpus of Spontaneous Japanese (CSJ), which has been developed in the five-year national project and will be the largest spontaneous speech databases. Expand

Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization

Yoshiaki Bando, M. Mimura, K. Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara
Computer Science, Engineering
IEEE International Conference on Acoustics…
31 October 2017

This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. Expand

An Unsupervised Model for Joint Phrase Alignment and Extraction

Graham Neubig, Taro Watanabe, E. Sumita, Shinsuke Mori, Tatsuya Kawahara
Computer Science
ACL
19 June 2011

We present an unsupervised model for joint phrase alignment and extraction using non-parametric Bayesian methods and inversion transduction grammars (ITGs). Expand

Bayesian Learning of a Language Model from Continuous Speech

Graham Neubig, M. Mimura, Shinsuke Mori, Tatsuya Kawahara
Computer Science
IEICE Trans. Inf. Syst.
1 February 2012

We propose a novel scheme to learn a language model (LM) for automatic speech recognition (ASR) directly from continuous speech. Expand

Recent progress of open-source LVCSR engine julius and Japanese model repository

Tatsuya Kawahara, A. Lee, K. Takeda, K. Itou, K. Shikano
Computer Science
INTERSPEECH
1 October 2004

We developed a free sharable platform that can be used as a baseline and reference for research and development. Expand

Free software toolkit for Japanese large vocabulary continuous speech recognition

Tatsuya Kawahara, A. Lee, +9 authors K. Shikano
Computer Science
INTERSPEECH
1 October 2000

We develop a free sharable platform that can be used as a baseline and reference for research and development. Expand

ERICA: The ERATO Intelligent Conversational Android

Dylan F. Glas, T. Minato, C. Ishi, Tatsuya Kawahara, H. Ishiguro
Computer Science
25th IEEE International Symposium on Robot and…
1 August 2016

In this paper we present an overview of the requirements and design of the platform, describe the development process of an interactive application, report on ERICA's first autonomous public demonstration, and discuss the main technical challenges that remain to be addressed in order to create humanlike, autonomous androids. Expand

Recommended Authors