Presentation	2005/12/15 Recent Progress of Large Vocabulary Continuous Speech Recognition Engine Julius Akinobu LEE,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Julius is a high-performance, two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech-related researchers and developers. It realizes almost real-time decoding on most current PCs on dictaion of over 60k words vocabulary. Julius has been developed to equip an open model interface, program portability, and sufficient recognition performance to be used both for the current research of speech recognition and for the development of speech-recognition-driven applications on real world. It has been developed continuously, integrating many required features and improving stability. This paper summarizes the recent progress of the LVCSR engine Julius, with brief description about the search algorithm.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	LVCSR / Julius / word graph / Gaussian mixture model / speech interface
Paper #	NLC2005-78,SP2005-111
Date of Issue

Conference Information
Committee	NLC
Conference Date	2005/12/15(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Natural Language Understanding and Models of Communication (NLC)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Recent Progress of Large Vocabulary Continuous Speech Recognition Engine Julius
Sub Title (in English)
Keyword(1)	LVCSR
Keyword(2)	Julius
Keyword(3)	word graph
Keyword(4)	Gaussian mixture model
Keyword(5)	speech interface
1st Author's Name	Akinobu LEE
1st Author's Affiliation	Graduate School of Engineering, Nagoya Institute of Technology()
Date	2005/12/15
Paper #	NLC2005-78,SP2005-111
Volume (vol)	vol.105
Number (no)	494
Page	pp.pp.-
#Pages	6
Date of Issue