Embedded JULIUS on T-Engine Platform


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/8195

Title:	Embedded JULIUS on T-Engine Platform
Authors:	Nobuo Hataoka Hiroaki Kokubo Akinobu Lee Tatsuya Kawahara Kiyohiro Shikano
Keywords:	Automatic Speech Recognition (ASR) Continuous Speech Recognition (CSR) Julius: Free CSR Software Embedded Julius Hardware Platform T-Engine SuperH Microprocessor GMS (Gaussian Mixture Selection) HMMs(Hidden Markov Models)
Issue Date:	Dec-2006
Publisher:	IEEE
Start page:	45
End page:	50
Abstract:	In this paper, we report implemental results of an embedded version of Julius. We used T-Enginetrade as a hardware platform which has a SuperH microprocessor. The Julius is free and open continuous speech recognition (CSR) software running on personal computers (PCs) which have huge CPU power and storage memory size. The technical problems to make Julius for embedded version are computing/process and memory reductions of Julius software. We realized 2.23 of RTF (real time factor) of embedded speech recognition processing on the condition of 5000-word vocabulary without any recognition accuracy degradation.
Description:	ISPACS2006: International Symposium on Intelligent Signal Processing and Communication Systems, December 12-15, 2006, Yonago, Japan.
URI:	http://hdl.handle.net/10061/8195
ISBN:	0780397320
Rights:	Copyright 2006 IEEE
Text Version:	Publisher
Publisher DOI:	10.1109/ISPACS.2006.364832
Appears in Collections:	情報科学研究科 / Graduate School of Information Science

Files in This Item:

File	Size	Format
ISPACS_2006_45.pdf	786.81 kB	Adobe PDF	View/Open