Evaluation of wavelet filters for speech recognition

Kidae Kim, Dae Hee Youn, Chul Hee Lee

Research output: Contribution to journalConference article

16 Citations (Scopus)

Abstract

Since wavelet decomposition of signal provides more flexible time-frequency resolutions, it can be utilized as a feature set for speech recognition. In this paper, we explore the possibility to use wavelet decomposition for speech recognition. In particular, we investigate a modified octave structured 5-level filter bank and the HMM (Hidden Markov Model) is used as a recognizer. We present an analysis of various wavelet filters for speech recognition and compare the results with the conventional features that include LPC and mel-cepstrums.

Original languageEnglish
Pages (from-to)2891-2894
Number of pages4
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume4
Publication statusPublished - 2000 Dec 1
Event2000 IEEE International Conference on Systems, Man and Cybernetics - Nashville, TN, USA
Duration: 2000 Oct 82000 Oct 11

Fingerprint

Speech recognition
Wavelet decomposition
Filter banks
Hidden Markov models

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Hardware and Architecture

Cite this

@article{b1f09ada15dc439485976ec135999684,
title = "Evaluation of wavelet filters for speech recognition",
abstract = "Since wavelet decomposition of signal provides more flexible time-frequency resolutions, it can be utilized as a feature set for speech recognition. In this paper, we explore the possibility to use wavelet decomposition for speech recognition. In particular, we investigate a modified octave structured 5-level filter bank and the HMM (Hidden Markov Model) is used as a recognizer. We present an analysis of various wavelet filters for speech recognition and compare the results with the conventional features that include LPC and mel-cepstrums.",
author = "Kidae Kim and Youn, {Dae Hee} and Lee, {Chul Hee}",
year = "2000",
month = "12",
day = "1",
language = "English",
volume = "4",
pages = "2891--2894",
journal = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
issn = "0884-3627",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Evaluation of wavelet filters for speech recognition. / Kim, Kidae; Youn, Dae Hee; Lee, Chul Hee.

In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Vol. 4, 01.12.2000, p. 2891-2894.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Evaluation of wavelet filters for speech recognition

AU - Kim, Kidae

AU - Youn, Dae Hee

AU - Lee, Chul Hee

PY - 2000/12/1

Y1 - 2000/12/1

N2 - Since wavelet decomposition of signal provides more flexible time-frequency resolutions, it can be utilized as a feature set for speech recognition. In this paper, we explore the possibility to use wavelet decomposition for speech recognition. In particular, we investigate a modified octave structured 5-level filter bank and the HMM (Hidden Markov Model) is used as a recognizer. We present an analysis of various wavelet filters for speech recognition and compare the results with the conventional features that include LPC and mel-cepstrums.

AB - Since wavelet decomposition of signal provides more flexible time-frequency resolutions, it can be utilized as a feature set for speech recognition. In this paper, we explore the possibility to use wavelet decomposition for speech recognition. In particular, we investigate a modified octave structured 5-level filter bank and the HMM (Hidden Markov Model) is used as a recognizer. We present an analysis of various wavelet filters for speech recognition and compare the results with the conventional features that include LPC and mel-cepstrums.

UR - http://www.scopus.com/inward/record.url?scp=0034513064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034513064&partnerID=8YFLogxK

M3 - Conference article

VL - 4

SP - 2891

EP - 2894

JO - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

JF - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

SN - 0884-3627

ER -