• Publications
  • Influence
Julius - an open source real-time large vocabulary recognition engine
TLDR
EUROSPEECH2001: the 7th European Conference on Speech Communication and Technology, September 3-7, 2001, Aalborg, Denmark. Expand
  • 620
  • 52
  • PDF
Recent Development of Open-Source Speech Recognition Engine Julius
TLDR
Julius is an open-source large-vocabulary speech recognition software used for both academic research and industrial applications. Expand
  • 308
  • 25
  • PDF
Overview of the IR for Spoken Documents Task in NTCIR-9 Workshop
TLDR
This paper describes an overview of the IR for Spoken Documents Task in NTCIR-9 Workshop. Expand
  • 76
  • 16
  • PDF
Benchmark test for speech recognition using the Corpus of Spontaneous Japanese
TLDR
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
  • 99
  • 12
  • PDF
Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization
TLDR
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
  • 53
  • 10
  • PDF
An Unsupervised Model for Joint Phrase Alignment and Extraction
TLDR
We present an unsupervised model for joint phrase alignment and extraction using non-parametric Bayesian methods and inversion transduction grammars (ITGs). Expand
  • 84
  • 9
  • PDF
Bayesian Learning of a Language Model from Continuous Speech
TLDR
We propose a novel scheme to learn a language model (LM) for automatic speech recognition (ASR) directly from continuous speech. Expand
  • 30
  • 7
  • PDF
Recent progress of open-source LVCSR engine julius and Japanese model repository
TLDR
We developed a free sharable platform that can be used as a baseline and reference for research and development. Expand
  • 62
  • 6
  • PDF
Free software toolkit for Japanese large vocabulary continuous speech recognition
TLDR
We develop a free sharable platform that can be used as a baseline and reference for research and development. Expand
  • 105
  • 5
  • PDF
ERICA: The ERATO Intelligent Conversational Android
TLDR
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
  • 64
  • 5
  • PDF
...
1
2
3
4
5
...