Publication detail

Effect of normalization on TRAP based systems in ASR

GRÉZL, F.

Original Title

Effect of normalization on TRAP based systems in ASR

Type

conference paper

Language

English

Original Abstract

 Good performance in noisy conditions is one of the most important
attributes of automatic speech recognition (ASR) system in practical
applications. We are focusing on the effect of the on-line mean and
variance normalization of temporal vectors in this work. We are comparing
the performance of the Temporal Pattern (TRAP) system with different kinds of
normalization in different noisy conditions. The performance of system
with temporal vectors projected on basis obtained by linear
discriminant analysis (LDA) is also investigated. Experiments show
better performance of system using vector projection in noisy conditions.

Keywords

normalization, noisy speech recognition, TRAP, feature extraction

Authors

GRÉZL, F.

RIV year

2003

Released

6. 5. 2003

Publisher

Department of Radioelectronics FEEC BUT

Location

Brno

ISBN

80-214-2383-8

Book

Proc. 13th International scientific conference Radioelektronika 2003

Pages from

128

Pages to

131

Pages count

4

BibTex

@inproceedings{BUT14206,
  author="František {Grézl}",
  title="Effect of normalization on TRAP based systems in ASR",
  booktitle="Proc. 13th International scientific conference Radioelektronika 2003",
  year="2003",
  pages="128--131",
  publisher="Department of Radioelectronics FEEC BUT",
  address="Brno",
  isbn="80-214-2383-8"
}