Publication detail

An Environment for Automatic Speech Signal Labeling

SIGMUND, M., MATĚJKA, P.

Original Title

An Environment for Automatic Speech Signal Labeling

English Title

An Environment for Automatic Speech Signal Labeling

Type

conference paper

Language

en

Original Abstract

In this paper, we present a new software environment for automatic labeling of spoken language. The labeling algorithm is based on the comparison of a set of speech parameters obtained either by the direct or by the cumulative method in the stable portion of each phoneme in the utterance. Testing the program on Czech speech signal, the best total segment detection rate of 90 % was achieved.

English abstract

In this paper, we present a new software environment for automatic labeling of spoken language. The labeling algorithm is based on the comparison of a set of speech parameters obtained either by the direct or by the cumulative method in the stable portion of each phoneme in the utterance. Testing the program on Czech speech signal, the best total segment detection rate of 90 % was achieved.

Keywords

speech signal, automatic labeling

RIV year

2002

Released

18.02.2002

Publisher

ACTA Press

Location

Innsbruck

ISBN

0-88986-324-5

Book

Applied Informatics

Pages from

298

Pages to

301

Pages count

4

Documents

BibTex


@inproceedings{BUT5470,
  author="Milan {Sigmund} and Pavel {Matějka}",
  title="An Environment for Automatic Speech Signal Labeling",
  annote="In this paper, we present a new software environment for automatic labeling of spoken language. The labeling algorithm is based on the comparison of a set of speech parameters obtained either by the direct or by the cumulative method in the stable portion of each phoneme in the utterance. Testing the program on Czech speech signal, the best total segment detection rate of 90 % was achieved.",
  address="ACTA Press",
  booktitle="Applied Informatics",
  chapter="5470",
  institution="ACTA Press",
  year="2002",
  month="february",
  pages="298",
  publisher="ACTA Press",
  type="conference paper"
}