Publication detail

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

HEŘMANSKÝ, H., GRÉZL, F.

Original Title

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

English Title

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

Type

conference paper

Language

en

Original Abstract

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.

English abstract

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.

Keywords

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

RIV year

2003

Released

23.09.2003

Publisher

Institute for Perceptual Artificial Intelligence

Location

Geneva

ISBN

1018-4074

Periodical

European Conference EUROSPEECH

Year of study

2003

Number

9

State

CH

Pages count

4

URL

Documents

BibTex


@inproceedings{BUT14205,
  author="František {Grézl} and Hynek {Heřmanský}",
  title="Local averaging and differentiating of spectral plane for TRAP-based ASR",
  annote="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.

", address="Institute for Perceptual Artificial Intelligence", booktitle="Proc. EUROSPEECH 2003", chapter="14205", institution="Institute for Perceptual Artificial Intelligence", journal="5th European Conference EUROSPEECH 97", number="9", year="2003", month="september", pages="0", publisher="Institute for Perceptual Artificial Intelligence", type="conference paper" }