Multi-level Segmentation of Natural Continuous Speech Using Different Auditory Front-ends

Helge Bjarup Dissing Sørensen; P. Dalsgaard

Multi-level Segmentation of Natural Continuous Speech Using Different Auditory Front-ends

Helge Bjarup Dissing Sørensen
, P. Dalsgaard

Aalborg University
Unknown

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Discusses acoustic-phonetic segmentation of speech signals to be used in a continuous speech recognition system. The goal of segmentation is to transform the continuous speech signal into a discrete set of segments each describing an acoustic event which corresponds to a homogeneous sound element. Recent years of research into multi-level segmentation of continuous speech has used either a neurophysiological auditory model or a Fourier transform as front-end processing. The paper describes and presents results obtained from a system configuration consisting of a psychoacoustic auditory model and a multi-level segmentation algorithm. Furthermore this alternative system is modified and compared to multi-level segmentation using an original/modified neurophysiological auditory model. All results are based on analysis of a large database of a naturally spoken continuous speech

Original language	English
Title of host publication	Eurospeech 89
Publisher	CEP Consultants
Publication date	1989
Publication status	Published - 1989
Externally published	Yes
Event	1st European Conference on Speech Communication and Technology - Paris, France Duration: 26 Sept 1989 → 28 Sept 1989 Conference number: 1 http://www.informatik.uni-trier.de/~ley/db/conf/interspeech/eurospeech1989.html

Conference

Conference	1st European Conference on Speech Communication and Technology
Number	1
Country/Territory	France
City	Paris
Period	26/09/1989 → 28/09/1989
Internet address	http://www.informatik.uni-trier.de/~ley/db/conf/interspeech/eurospeech1989.html

OpenUrl availability

Check availability in DTU Findit

Cite this

@inproceedings{869eea4149fc49a9881baa3e98fb055f,

title = "Multi-level Segmentation of Natural Continuous Speech Using Different Auditory Front-ends",

abstract = "Discusses acoustic-phonetic segmentation of speech signals to be used in a continuous speech recognition system. The goal of segmentation is to transform the continuous speech signal into a discrete set of segments each describing an acoustic event which corresponds to a homogeneous sound element. Recent years of research into multi-level segmentation of continuous speech has used either a neurophysiological auditory model or a Fourier transform as front-end processing. The paper describes and presents results obtained from a system configuration consisting of a psychoacoustic auditory model and a multi-level segmentation algorithm. Furthermore this alternative system is modified and compared to multi-level segmentation using an original/modified neurophysiological auditory model. All results are based on analysis of a large database of a naturally spoken continuous speech",

author = "S{\o}rensen, \{Helge Bjarup Dissing\} and P. Dalsgaard",

year = "1989",

language = "English",

booktitle = "Eurospeech 89",

publisher = "CEP Consultants",

note = "1st European Conference on Speech Communication and Technology, EUROSPEECH 1989 ; Conference date: 26-09-1989 Through 28-09-1989",

url = "http://www.informatik.uni-trier.de/\textasciitilde{}ley/db/conf/interspeech/eurospeech1989.html",

}

TY - GEN

T1 - Multi-level Segmentation of Natural Continuous Speech Using Different Auditory Front-ends

AU - Sørensen, Helge Bjarup Dissing

AU - Dalsgaard, P.

N1 - Conference code: 1

PY - 1989

Y1 - 1989

N2 - Discusses acoustic-phonetic segmentation of speech signals to be used in a continuous speech recognition system. The goal of segmentation is to transform the continuous speech signal into a discrete set of segments each describing an acoustic event which corresponds to a homogeneous sound element. Recent years of research into multi-level segmentation of continuous speech has used either a neurophysiological auditory model or a Fourier transform as front-end processing. The paper describes and presents results obtained from a system configuration consisting of a psychoacoustic auditory model and a multi-level segmentation algorithm. Furthermore this alternative system is modified and compared to multi-level segmentation using an original/modified neurophysiological auditory model. All results are based on analysis of a large database of a naturally spoken continuous speech

AB - Discusses acoustic-phonetic segmentation of speech signals to be used in a continuous speech recognition system. The goal of segmentation is to transform the continuous speech signal into a discrete set of segments each describing an acoustic event which corresponds to a homogeneous sound element. Recent years of research into multi-level segmentation of continuous speech has used either a neurophysiological auditory model or a Fourier transform as front-end processing. The paper describes and presents results obtained from a system configuration consisting of a psychoacoustic auditory model and a multi-level segmentation algorithm. Furthermore this alternative system is modified and compared to multi-level segmentation using an original/modified neurophysiological auditory model. All results are based on analysis of a large database of a naturally spoken continuous speech

M3 - Article in proceedings

BT - Eurospeech 89

PB - CEP Consultants

T2 - 1st European Conference on Speech Communication and Technology

Y2 - 26 September 1989 through 28 September 1989

ER -

Multi-level Segmentation of Natural Continuous Speech Using Different Auditory Front-ends

Abstract

Conference

OpenUrl availability

Fingerprint

Cite this