Optimizing feature extraction for English word recognition

Euisun Choi, Donghoon Hyun, Chulhee Lee

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

In this paper, we investigate the possibility to improve the recognition accuracy of English words by optimizing feature extraction. The optimization method is based on the simplex algorithm. Although the mel-cepstrum obtained by the critical band filters reflects the human auditory perception, it may not be the optimal features for speech recognition. In this paper, we show that the mel-cepstrum can be optimized in terms of recognition accuracy by adjusting the center frequencies and bandwidths of the critical filters. Experiments with English words showed that the optimized filter bank provide a noticeable performance improvement.

Original languageEnglish
Pages (from-to)I/813-I/816
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1
Publication statusPublished - 2002 Jul 11
Event2002 IEEE International Conference on Acustics, Speech, and Signal Processing - Orlando, FL, United States
Duration: 2002 May 132002 May 17

Fingerprint

Filter banks
Speech recognition
pattern recognition
Feature extraction
Bandwidth
filters
auditory perception
Experiments
speech recognition
adjusting
bandwidth
optimization

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

@article{bd2d3e35c93d406b97f787b939d1149c,
title = "Optimizing feature extraction for English word recognition",
abstract = "In this paper, we investigate the possibility to improve the recognition accuracy of English words by optimizing feature extraction. The optimization method is based on the simplex algorithm. Although the mel-cepstrum obtained by the critical band filters reflects the human auditory perception, it may not be the optimal features for speech recognition. In this paper, we show that the mel-cepstrum can be optimized in terms of recognition accuracy by adjusting the center frequencies and bandwidths of the critical filters. Experiments with English words showed that the optimized filter bank provide a noticeable performance improvement.",
author = "Euisun Choi and Donghoon Hyun and Chulhee Lee",
year = "2002",
month = "7",
day = "11",
language = "English",
volume = "1",
pages = "I/813--I/816",
journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",
issn = "0736-7791",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Optimizing feature extraction for English word recognition. / Choi, Euisun; Hyun, Donghoon; Lee, Chulhee.

In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 1, 11.07.2002, p. I/813-I/816.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Optimizing feature extraction for English word recognition

AU - Choi, Euisun

AU - Hyun, Donghoon

AU - Lee, Chulhee

PY - 2002/7/11

Y1 - 2002/7/11

N2 - In this paper, we investigate the possibility to improve the recognition accuracy of English words by optimizing feature extraction. The optimization method is based on the simplex algorithm. Although the mel-cepstrum obtained by the critical band filters reflects the human auditory perception, it may not be the optimal features for speech recognition. In this paper, we show that the mel-cepstrum can be optimized in terms of recognition accuracy by adjusting the center frequencies and bandwidths of the critical filters. Experiments with English words showed that the optimized filter bank provide a noticeable performance improvement.

AB - In this paper, we investigate the possibility to improve the recognition accuracy of English words by optimizing feature extraction. The optimization method is based on the simplex algorithm. Although the mel-cepstrum obtained by the critical band filters reflects the human auditory perception, it may not be the optimal features for speech recognition. In this paper, we show that the mel-cepstrum can be optimized in terms of recognition accuracy by adjusting the center frequencies and bandwidths of the critical filters. Experiments with English words showed that the optimized filter bank provide a noticeable performance improvement.

UR - http://www.scopus.com/inward/record.url?scp=0036289787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036289787&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0036289787

VL - 1

SP - I/813-I/816

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

SN - 0736-7791

ER -