Classification of fricatives using feature extrapolation of acoustic-phonetic features in telephone speech

Jung Won Lee, Jeung Yoon Choi, Hong Goo Kang

Research output: Contribution to journalConference article

2 Citations (Scopus)

Abstract

This paper proposes a classification module for fricative consonants in telephone speech using an acoustic-phonetic feature extrapolation technique. In channel-deteriorated telephone speech, acoustic cues of fricative consonants are expected to be degraded or missing due to limited bandwidth. This paper applies an extrapolation technique to acoustic-phonetic features based on Gaussian mixture models, which uses a statistical learning of the correspondence between acoustic-phonetic features of wideband speech and the spectral characteristics of telephone bandwidth speech. Experimental results with NTIMIT database verify that feature extrapolation improves the performance of fricative classification module for all unvoiced fricatives by around 10% (relative error) compared to the performance obtained by only acoustic-phonetic features extracted from the narrowband signal.

Original languageEnglish
Pages (from-to)1261-1264
Number of pages4
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2011 Dec 1
Event12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 - Florence, Italy
Duration: 2011 Aug 272011 Aug 31

Fingerprint

Speech analysis
Telephone
Extrapolation
Acoustics
Bandwidth
Module
Statistical Learning
Gaussian Mixture Model
Relative Error
Correspondence
Speech
Acoustic Phonetics
Phonetic Features
Fricatives
Verify
Experimental Results
Consonant

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

Cite this

@article{2ef42cec153a4c87ae3ad31b37c6ca14,
title = "Classification of fricatives using feature extrapolation of acoustic-phonetic features in telephone speech",
abstract = "This paper proposes a classification module for fricative consonants in telephone speech using an acoustic-phonetic feature extrapolation technique. In channel-deteriorated telephone speech, acoustic cues of fricative consonants are expected to be degraded or missing due to limited bandwidth. This paper applies an extrapolation technique to acoustic-phonetic features based on Gaussian mixture models, which uses a statistical learning of the correspondence between acoustic-phonetic features of wideband speech and the spectral characteristics of telephone bandwidth speech. Experimental results with NTIMIT database verify that feature extrapolation improves the performance of fricative classification module for all unvoiced fricatives by around 10{\%} (relative error) compared to the performance obtained by only acoustic-phonetic features extracted from the narrowband signal.",
author = "Lee, {Jung Won} and Choi, {Jeung Yoon} and Kang, {Hong Goo}",
year = "2011",
month = "12",
day = "1",
language = "English",
pages = "1261--1264",
journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
issn = "2308-457X",

}

TY - JOUR

T1 - Classification of fricatives using feature extrapolation of acoustic-phonetic features in telephone speech

AU - Lee, Jung Won

AU - Choi, Jeung Yoon

AU - Kang, Hong Goo

PY - 2011/12/1

Y1 - 2011/12/1

N2 - This paper proposes a classification module for fricative consonants in telephone speech using an acoustic-phonetic feature extrapolation technique. In channel-deteriorated telephone speech, acoustic cues of fricative consonants are expected to be degraded or missing due to limited bandwidth. This paper applies an extrapolation technique to acoustic-phonetic features based on Gaussian mixture models, which uses a statistical learning of the correspondence between acoustic-phonetic features of wideband speech and the spectral characteristics of telephone bandwidth speech. Experimental results with NTIMIT database verify that feature extrapolation improves the performance of fricative classification module for all unvoiced fricatives by around 10% (relative error) compared to the performance obtained by only acoustic-phonetic features extracted from the narrowband signal.

AB - This paper proposes a classification module for fricative consonants in telephone speech using an acoustic-phonetic feature extrapolation technique. In channel-deteriorated telephone speech, acoustic cues of fricative consonants are expected to be degraded or missing due to limited bandwidth. This paper applies an extrapolation technique to acoustic-phonetic features based on Gaussian mixture models, which uses a statistical learning of the correspondence between acoustic-phonetic features of wideband speech and the spectral characteristics of telephone bandwidth speech. Experimental results with NTIMIT database verify that feature extrapolation improves the performance of fricative classification module for all unvoiced fricatives by around 10% (relative error) compared to the performance obtained by only acoustic-phonetic features extracted from the narrowband signal.

UR - http://www.scopus.com/inward/record.url?scp=84865731614&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865731614&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84865731614

SP - 1261

EP - 1264

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SN - 2308-457X

ER -