Memory efficient and fast speech recognition system for lowresource mobile devices

In this paper, we consider practical issues such as memory efficiency and fast decoding to make continuous density hidden Markov model (CDHMM)-based large vocabulary speech recognition system work on resource limited mobile devices. Particularly, we focus on memory efficient acoustic modeling and fa...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on consumer electronics 2006-08, Vol.52 (3), p.792-796
Main Authors: Chung, I., Chung, I.-J.
Format: Article
Language:English
Subjects:
Acoustic devices
Computer interfaces
Decoding
Density
Electronics
Gaussian
Hidden Markov models
Keyboards
Microprocessors
Mobile communication systems
Mobile computing
Personal digital assistants
Probability
Running
Speech recognition
Tasks
Vocabulary
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we consider practical issues such as memory efficiency and fast decoding to make continuous density hidden Markov model (CDHMM)-based large vocabulary speech recognition system work on resource limited mobile devices. Particularly, we focus on memory efficient acoustic modeling and fast state likelihood computation. The proposed techniques are implemented in a speaker-independent Korean speech recognition system running on a personal digital assistant (PDA) with a 32-bit fixed-point processor operating at 400 MHz. The system uses 0.5 MB memory for representing 28448 Gaussians and it runs at 2.54xRT without serious degradation of accuracy on 10 k phonetically optimized words recognition task domain
ISSN:0098-3063
1558-4127
DOI:10.1109/TCE.2006.1706471