A NEURAL NETWORK USING NON-UNIFORM UNITS FOR CONTINUOUS SPEECH RECOGNITION

Ha Jin Yu; Yung Hwan Oh

A NEURAL NETWORK USING NON-UNIFORM UNITS FOR CONTINUOUS SPEECH RECOGNITION

Ha Jin Yu, Yung Hwan Oh

Department of Computer Science and Engineering

Korea Advanced Institute of Science and Technology

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

A new network model, U-net, is proposed to recognize continuous speech, based on the non-uniform unit which is a kind of acoustic sub-word unit. In this model, input speech can be segmented into units by using a part of the network before classification. The unit has steady states at the boundaries and a transient state in the middle. The network structure is designed according to the structure of the unit. The steady states and transient state are recognized by separate networks and different feature parameters are used. For the transient part a delta parameter is used. The segmentation net is trained to reduce the number of unit classes.

Original language	English
Pages	1677-1680
Number of pages	4
State	Published - 1995
Event	4th European Conference on Speech Communication and Technology, EUROSPEECH 1995 - Madrid, Spain Duration: 18 Sep 1995 → 21 Sep 1995

Conference

Conference	4th European Conference on Speech Communication and Technology, EUROSPEECH 1995
Country/Territory	Spain
City	Madrid
Period	18/09/95 → 21/09/95

Cite this

@conference{0301fb1d29454d44a0dae310c186f1ab,

title = "A NEURAL NETWORK USING NON-UNIFORM UNITS FOR CONTINUOUS SPEECH RECOGNITION",

abstract = "A new network model, U-net, is proposed to recognize continuous speech, based on the non-uniform unit which is a kind of acoustic sub-word unit. In this model, input speech can be segmented into units by using a part of the network before classification. The unit has steady states at the boundaries and a transient state in the middle. The network structure is designed according to the structure of the unit. The steady states and transient state are recognized by separate networks and different feature parameters are used. For the transient part a delta parameter is used. The segmentation net is trained to reduce the number of unit classes.",

author = "Yu, {Ha Jin} and Oh, {Yung Hwan}",

note = "Publisher Copyright: {\textcopyright} 1995 4th European Conference on Speech Communication and Technology, EUROSPEECH 1995. All rights reserved.; 4th European Conference on Speech Communication and Technology, EUROSPEECH 1995 ; Conference date: 18-09-1995 Through 21-09-1995",

year = "1995",

language = "English",

pages = "1677--1680",

}

TY - CONF

T1 - A NEURAL NETWORK USING NON-UNIFORM UNITS FOR CONTINUOUS SPEECH RECOGNITION

AU - Yu, Ha Jin

AU - Oh, Yung Hwan

PY - 1995

Y1 - 1995

N2 - A new network model, U-net, is proposed to recognize continuous speech, based on the non-uniform unit which is a kind of acoustic sub-word unit. In this model, input speech can be segmented into units by using a part of the network before classification. The unit has steady states at the boundaries and a transient state in the middle. The network structure is designed according to the structure of the unit. The steady states and transient state are recognized by separate networks and different feature parameters are used. For the transient part a delta parameter is used. The segmentation net is trained to reduce the number of unit classes.

AB - A new network model, U-net, is proposed to recognize continuous speech, based on the non-uniform unit which is a kind of acoustic sub-word unit. In this model, input speech can be segmented into units by using a part of the network before classification. The unit has steady states at the boundaries and a transient state in the middle. The network structure is designed according to the structure of the unit. The steady states and transient state are recognized by separate networks and different feature parameters are used. For the transient part a delta parameter is used. The segmentation net is trained to reduce the number of unit classes.

UR - http://www.scopus.com/inward/record.url?scp=0342843475&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0342843475

SP - 1677

EP - 1680

T2 - 4th European Conference on Speech Communication and Technology, EUROSPEECH 1995

Y2 - 18 September 1995 through 21 September 1995

ER -

A NEURAL NETWORK USING NON-UNIFORM UNITS FOR CONTINUOUS SPEECH RECOGNITION

Abstract

Conference

Other files and links

Fingerprint

Cite this