Tatsuya Kawahara

Publications
Influence

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

Akinobu Lee, Tatsuya Kawahara, Kiyohiro Shikano

Computer Science

INTERSPEECH

2001 (First Published: 1 September 2001)

Julius is a high-performance, two-pass LVCSR decoder for researchers and developers. Based on word 3-gram and context-dependent HMM, it can perform almost realtime decoding on most current PCs in 20k… Continue Reading

Recent Development of Open-Source Speech Recognition Engine Julius

Akinobu Lee, Tatsuya Kawahara

Computer Science

2009 (First Published: 4 October 2009)

Julius is an open-source large-vocabulary speech recognition software used for both academic research and industrial applications. It executes real-time speech recognition of a 60k-word dictation… Continue Reading

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… Continue Reading

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

Tomoyosi Akiba, Hiromitsu Nishizaki, Kiyoaki Aikawa, Tatsuya Kawahara, Tomoko Matsui

Computer Science

NTCIR

2011

This paper describes an overview of the IR for Spoken Documents Task in NTCIR-9 Workshop. In this task, the spoken term detection (STD) subtask and ad-hoc spoken document retrieval subtask (SDR) are… Continue Reading

An Unsupervised Model for Joint Phrase Alignment and Extraction

Graham Neubig, Taro Watanabe, Eiichiro Sumita, Shinsuke Mori, Tatsuya Kawahara

Computer Science

ACL

2011 (First Published: 1 June 2011)

We present an unsupervised model for joint phrase alignment and extraction using non-parametric Bayesian methods and inversion transduction grammars (ITGs). The key contribution is that phrases of… Continue Reading

Gaussian mixture selection using context-independent HMM

Akinobu Lee, Tatsuya Kawahara, Kiyohiro Shikano

Computer Science

2001

We address a method to efficiently select Gaussian mixtures for fast acoustic likelihood computation. It makes use of context-independent models for selection and back-off of corresponding triphone… Continue Reading

Bayesian Learning of a Language Model from Continuous Speech

Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsuya Kawahara

Computer Science

IEICE Transactions

2012

We propose a novel scheme to learn a language model (LM) for automatic speech recognition (ASR) directly from continuous speech. In the proposed method, we first generate phoneme lattices using an… Continue Reading

Voice activity detection based on optimally weighted combination of multiple features

Yusuke Kida, Tatsuya Kawahara

Computer Science

INTERSPEECH

2005

A touch response apparatus for an electronic musical instrument wherein a nonlinear analog-to-digital conversion is effected using a single A/D converter in correspondence with a plurality of keys,… Continue Reading

Free software toolkit for Japanese large vocabulary continuous speech recognition

Tatsuya Kawahara, Akinobu Lee, +9 authors Kiyohiro Shikano

Computer Science

INTERSPEECH

2000

ICSLP2000: the 6th International Conference on Spoken Language Processing, October 16-20, 2000, Beijing, China.

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

Tatsuya Kawahara, Akinobu Lee, Kazuya Takeda, Katsunobu Itou, Kiyohiro Shikano

Computer Science

INTERSPEECH

2004 (First Published: 1 October 2004)

ICSLP2004: the 8th International Conference on Spoken Language Processing, October 4-8, 2004, Jeju Island, Korea.