An on-line adaptive neural network for speech recognition

Li Peng Zhang; Li Me Li; Zheru Chi

doi:10.1007/BF02111211

An on-line adaptive neural network for speech recognition

Li Peng Zhang, Li Me Li, Zheru Chi

The Hong Kong Polytechnic University

Research output: Journal article publication › Journal article › Academic research › peer-review

1 Citation (Scopus)

Abstract

In this paper, we present an on-line learning neural network model, Dynamic Recognition Neural Network (DRNN), for real-time speech recognition. The property of accumulative learning of the DRNN makes it very suitable for real-time speech recognition with on-line learning. A comparison between the DRNN and Hidden Markov Model (HMM) shows that the computational complexity of the former is lower than that of the latter in both training and recognition. Encouraging results are obtained when the DRNN is tested on a BUPT digit database (Mandarin) and on the on-line learning of twenty isolated English computer command words.

Original language	English
Pages (from-to)	241-248
Number of pages	8
Journal	International Journal of Speech Technology
Volume	2
Issue number	3
DOIs	https://doi.org/10.1007/BF02111211
Publication status	Published - 1 Jan 1998

Keywords

Accumulative learning
Adaptive neural networks
Dynamic recognition neural network (DRNN)
Hidden markov model
Speech recognition

ASJC Scopus subject areas

Software
Language and Linguistics
Human-Computer Interaction
Linguistics and Language
Computer Vision and Pattern Recognition

More information

10.1007/BF02111211

Cite this

@article{80c53d273ea8423f9ab0cd9955a0ebd2,

title = "An on-line adaptive neural network for speech recognition",

abstract = "In this paper, we present an on-line learning neural network model, Dynamic Recognition Neural Network (DRNN), for real-time speech recognition. The property of accumulative learning of the DRNN makes it very suitable for real-time speech recognition with on-line learning. A comparison between the DRNN and Hidden Markov Model (HMM) shows that the computational complexity of the former is lower than that of the latter in both training and recognition. Encouraging results are obtained when the DRNN is tested on a BUPT digit database (Mandarin) and on the on-line learning of twenty isolated English computer command words.",

keywords = "Accumulative learning, Adaptive neural networks, Dynamic recognition neural network (DRNN), Hidden markov model, Speech recognition",

author = "Zhang, {Li Peng} and Li, {Li Me} and Zheru Chi",

year = "1998",

month = jan,

day = "1",

doi = "10.1007/BF02111211",

language = "English",

volume = "2",

pages = "241--248",

journal = "International Journal of Speech Technology",

issn = "1381-2416",

publisher = "Springer Netherlands",

number = "3",

}

TY - JOUR

T1 - An on-line adaptive neural network for speech recognition

AU - Zhang, Li Peng

AU - Li, Li Me

AU - Chi, Zheru

PY - 1998/1/1

Y1 - 1998/1/1

N2 - In this paper, we present an on-line learning neural network model, Dynamic Recognition Neural Network (DRNN), for real-time speech recognition. The property of accumulative learning of the DRNN makes it very suitable for real-time speech recognition with on-line learning. A comparison between the DRNN and Hidden Markov Model (HMM) shows that the computational complexity of the former is lower than that of the latter in both training and recognition. Encouraging results are obtained when the DRNN is tested on a BUPT digit database (Mandarin) and on the on-line learning of twenty isolated English computer command words.

AB - In this paper, we present an on-line learning neural network model, Dynamic Recognition Neural Network (DRNN), for real-time speech recognition. The property of accumulative learning of the DRNN makes it very suitable for real-time speech recognition with on-line learning. A comparison between the DRNN and Hidden Markov Model (HMM) shows that the computational complexity of the former is lower than that of the latter in both training and recognition. Encouraging results are obtained when the DRNN is tested on a BUPT digit database (Mandarin) and on the on-line learning of twenty isolated English computer command words.

KW - Accumulative learning

KW - Adaptive neural networks

KW - Dynamic recognition neural network (DRNN)

KW - Hidden markov model

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=0032156325&partnerID=8YFLogxK

U2 - 10.1007/BF02111211

DO - 10.1007/BF02111211

M3 - Journal article

SN - 1381-2416

VL - 2

SP - 241

EP - 248

JO - International Journal of Speech Technology

JF - International Journal of Speech Technology

IS - 3

ER -

An on-line adaptive neural network for speech recognition

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this