Estimating phoneme formant targets and coarticulation parameters of conversational and clear speech

Brian O. Bush, Alexander Kain

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We present a data-driven formant model and methodology for discovering its parameters, namely phoneme targets and coarticulation functions for consonant-vowel-consonant (CVC) words from fully-automatic formant data. The model uses formant targets that are speaker dependent, but independent of speaking style and phonemic context. We used a global error measure to search for optimal formant targets for all phonemes, including classes of sounds where formants are not directly observable. Analysis of coarticulation parameters found significant differences in parameters between clear and conversational speech. Estimated formant targets were largely in agreement with acoustic-phonetic expectations. An intelligibility test validated that resynthesized CVC words using modeled formant trajectories were nearly as intelligible as resynthesized CVC words using observed formant trajectories.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages8017-8021
Number of pages5
DOIs
StatePublished - Oct 18 2013
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: May 26 2013May 31 2013

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CountryCanada
CityVancouver, BC
Period5/26/135/31/13

Fingerprint

Trajectories
Speech intelligibility
Speech analysis
Acoustics
Acoustic waves

Keywords

  • clear speech
  • coarticulation
  • formants

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Bush, B. O., & Kain, A. (2013). Estimating phoneme formant targets and coarticulation parameters of conversational and clear speech. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (pp. 8017-8021). [6639226] https://doi.org/10.1109/ICASSP.2013.6639226

Estimating phoneme formant targets and coarticulation parameters of conversational and clear speech. / Bush, Brian O.; Kain, Alexander.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 8017-8021 6639226.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bush, BO & Kain, A 2013, Estimating phoneme formant targets and coarticulation parameters of conversational and clear speech. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings., 6639226, pp. 8017-8021, 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, Vancouver, BC, Canada, 5/26/13. https://doi.org/10.1109/ICASSP.2013.6639226
Bush BO, Kain A. Estimating phoneme formant targets and coarticulation parameters of conversational and clear speech. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. p. 8017-8021. 6639226 https://doi.org/10.1109/ICASSP.2013.6639226
Bush, Brian O. ; Kain, Alexander. / Estimating phoneme formant targets and coarticulation parameters of conversational and clear speech. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. 2013. pp. 8017-8021
@inproceedings{b39674cecb8f44878846a834d7ba5fe4,
title = "Estimating phoneme formant targets and coarticulation parameters of conversational and clear speech",
abstract = "We present a data-driven formant model and methodology for discovering its parameters, namely phoneme targets and coarticulation functions for consonant-vowel-consonant (CVC) words from fully-automatic formant data. The model uses formant targets that are speaker dependent, but independent of speaking style and phonemic context. We used a global error measure to search for optimal formant targets for all phonemes, including classes of sounds where formants are not directly observable. Analysis of coarticulation parameters found significant differences in parameters between clear and conversational speech. Estimated formant targets were largely in agreement with acoustic-phonetic expectations. An intelligibility test validated that resynthesized CVC words using modeled formant trajectories were nearly as intelligible as resynthesized CVC words using observed formant trajectories.",
keywords = "clear speech, coarticulation, formants",
author = "Bush, {Brian O.} and Alexander Kain",
year = "2013",
month = "10",
day = "18",
doi = "10.1109/ICASSP.2013.6639226",
language = "English (US)",
isbn = "9781479903566",
pages = "8017--8021",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

}

TY - GEN

T1 - Estimating phoneme formant targets and coarticulation parameters of conversational and clear speech

AU - Bush, Brian O.

AU - Kain, Alexander

PY - 2013/10/18

Y1 - 2013/10/18

N2 - We present a data-driven formant model and methodology for discovering its parameters, namely phoneme targets and coarticulation functions for consonant-vowel-consonant (CVC) words from fully-automatic formant data. The model uses formant targets that are speaker dependent, but independent of speaking style and phonemic context. We used a global error measure to search for optimal formant targets for all phonemes, including classes of sounds where formants are not directly observable. Analysis of coarticulation parameters found significant differences in parameters between clear and conversational speech. Estimated formant targets were largely in agreement with acoustic-phonetic expectations. An intelligibility test validated that resynthesized CVC words using modeled formant trajectories were nearly as intelligible as resynthesized CVC words using observed formant trajectories.

AB - We present a data-driven formant model and methodology for discovering its parameters, namely phoneme targets and coarticulation functions for consonant-vowel-consonant (CVC) words from fully-automatic formant data. The model uses formant targets that are speaker dependent, but independent of speaking style and phonemic context. We used a global error measure to search for optimal formant targets for all phonemes, including classes of sounds where formants are not directly observable. Analysis of coarticulation parameters found significant differences in parameters between clear and conversational speech. Estimated formant targets were largely in agreement with acoustic-phonetic expectations. An intelligibility test validated that resynthesized CVC words using modeled formant trajectories were nearly as intelligible as resynthesized CVC words using observed formant trajectories.

KW - clear speech

KW - coarticulation

KW - formants

UR - http://www.scopus.com/inward/record.url?scp=84890515469&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890515469&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2013.6639226

DO - 10.1109/ICASSP.2013.6639226

M3 - Conference contribution

AN - SCOPUS:84890515469

SN - 9781479903566

SP - 8017

EP - 8021

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

ER -