Publication Details

Local averaging and differentiating of spectral plane for TRAP-based ASR

GRÉZL, F.; HEŘMANSKÝ, H. Local averaging and differentiating of spectral plane for TRAP-based ASR. Proc. EUROSPEECH 2003. European Conference EUROSPEECH. Geneva: Institute for Perceptual Artificial Intelligence, 2003. p. 0-0. ISSN: 1018-4074.
Czech title
Lokální průměrování a diferencování spektrální roviny pro na TRAPech zalozené ASR
Type
conference paper
Language
English
Authors
Grézl František, Ing., Ph.D. (DCGM)
Heřmanský Hynek, prof. Ing. (DCGM)
URL
Keywords

speech, speech processing, feature extraction ,speech recognittion, TRAP, TRAP modifications

Abstract

one dimensional averaging and diferentiating of spectral plane over time or frequency for TRAP based automatic speech recognition

Annotation

Local frequency and time averaging and differentiating operators,
using three neighboring points of critical-band time-frequency
plane, are used to process the plane prior to its use in
TRAP-based ASR. In that way, five alternative TRAP-based ASR
systems (the original one and the time/frequency
integrated/differentiated ones)are created. We show that the
frequency differentiating operator improves performance of the
TRAP-based ASR.

Published
2003
Pages
4
Journal
European Conference EUROSPEECH, vol. 2003, no. 9, ISSN 1018-4074
Proceedings
Proc. EUROSPEECH 2003
Publisher
Institute for Perceptual Artificial Intelligence
Place
Geneva
BibTeX 
@inproceedings{BUT14205,
  author="František {Grézl} and Hynek {Heřmanský}",
  title="Local averaging and differentiating of spectral plane for TRAP-based ASR",
  booktitle="Proc. EUROSPEECH 2003",
  year="2003",
  journal="European Conference EUROSPEECH",
  volume="2003",
  number="9",
  pages="4",
  publisher="Institute for Perceptual Artificial Intelligence",
  address="Geneva",
  issn="1018-4074",
  url="http://www.symporg.ch/eurospeech/"
}
Back to top