Result Details

Phoneme Classification using Temporal Patterns

MATĚJKA, P.; SCHWARZ, P.; GRÉZL, F.; ČERNOCKÝ, J. Phoneme Classification using Temporal Patterns. Proc. 13th International scientific conference Radioelektronika 2003. Brno: Faculty of Electrical Engineering and Communication BUT, 2003. p. 1-4. ISBN: 80-214-2383-8.

Type

conference paper

Language

English

Authors

Matějka Pavel, Ing., Ph.D.
Schwarz Petr, Ing., Ph.D.
Grézl František, Ing., Ph.D.
Černocký Jan, prof. Dr. Ing.

Abstract

Our goal is to improve recognition accuracy of phoneme recognizer. Weare trying to implement Temporal Pattern (TRAP) into our system. Furtherimprovement can be achieved by different training strategy. Our secondinterest are the rescoring techniques and their usage for phonemeclassification. Our experiments show promising results of this approach.

Keywords

phoneme classifying, feature extraction, temporal pattern

Published

2003

Pages

1–4

Proceedings

Proc. 13th International scientific conference Radioelektronika 2003

Conference

Radioelektronika 2003

ISBN

80-214-2383-8

Publisher

Faculty of Electrical Engineering and Communication BUT

Place

Brno

BibTeX

@inproceedings{BUT14185,
  author="Pavel {Matějka} and Petr {Schwarz} and František {Grézl} and Jan {Černocký}",
  title="Phoneme Classification using Temporal Patterns",
  booktitle="Proc. 13th International scientific conference Radioelektronika 2003",
  year="2003",
  pages="1--4",
  publisher="Faculty of Electrical Engineering and Communication BUT",
  address="Brno",
  isbn="80-214-2383-8"
}

Projects

Data driven and anthropic coding and recognition of speech, GACR, Postdoktorandské granty, GP102/02/D108, start: 2002-09-01, end: 2005-08-30, completed
Voice technologies for support of information society, GACR, Standardní projekty, GA102/02/0124, start: 2002-01-01, end: 2004-12-31, completed

Research groups

Speech Data Mining Research Group BUT Speech@FIT (RG SPEECH)

Departments

Department of Radio Electronics (UREL)
Faculty of Electrical Engineering and Communication (FEEC)
Faculty of Information Technology (FIT)