Use of the articulation index to design a wavelet packet-based method for improving speech intelligibility

Daniel M. Rasetshwane, J. Robert Boston, Ching Chung Li

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

1 Citation (Scopus)

Abstract

Speech transients are important cues for identifying and discriminating speech sounds, and several studies have suggested that selective amplification of these transients can improve the intelligibility of speech in noise. This paper describes an improved version of a wavelet-based method for extracting transient speech that we described in [9] and the use of the articulation index to select optimal parameters for the method. The new method combines subband decomposition by wavelet packets and transition rate characterization based on the first derivative of short-time energy. The method also incorporates a threshold which, when varied, controls the amount of quasi-steady-state activity that is included in the transient speech signal. The speech modification scheme is optimized and intelligibility improvement is estimated using the articulation index.

Original languageEnglish (US)
Title of host publication2007 15th International Conference on Digital Signal Processing, DSP 2007
Pages643-646
Number of pages4
DOIs
StatePublished - Dec 1 2007
Event2007 15th International Conference onDigital Signal Processing, DSP 2007 - Wales, United Kingdom
Duration: Jul 1 2007Jul 4 2007

Publication series

Name2007 15th International Conference on Digital Signal Processing, DSP 2007

Other

Other2007 15th International Conference onDigital Signal Processing, DSP 2007
CountryUnited Kingdom
CityWales
Period7/1/077/4/07

Fingerprint

Speech intelligibility
Amplification
Acoustic waves
Derivatives
Decomposition

Keywords

  • Articulation index
  • Speech enhancement
  • Transient speech

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Rasetshwane, D. M., Boston, J. R., & Li, C. C. (2007). Use of the articulation index to design a wavelet packet-based method for improving speech intelligibility. In 2007 15th International Conference on Digital Signal Processing, DSP 2007 (pp. 643-646). [4288664] (2007 15th International Conference on Digital Signal Processing, DSP 2007). https://doi.org/10.1109/ICDSP.2007.4288664

Use of the articulation index to design a wavelet packet-based method for improving speech intelligibility. / Rasetshwane, Daniel M.; Boston, J. Robert; Li, Ching Chung.

2007 15th International Conference on Digital Signal Processing, DSP 2007. 2007. p. 643-646 4288664 (2007 15th International Conference on Digital Signal Processing, DSP 2007).

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

Rasetshwane, DM, Boston, JR & Li, CC 2007, Use of the articulation index to design a wavelet packet-based method for improving speech intelligibility. in 2007 15th International Conference on Digital Signal Processing, DSP 2007., 4288664, 2007 15th International Conference on Digital Signal Processing, DSP 2007, pp. 643-646, 2007 15th International Conference onDigital Signal Processing, DSP 2007, Wales, United Kingdom, 7/1/07. https://doi.org/10.1109/ICDSP.2007.4288664
Rasetshwane DM, Boston JR, Li CC. Use of the articulation index to design a wavelet packet-based method for improving speech intelligibility. In 2007 15th International Conference on Digital Signal Processing, DSP 2007. 2007. p. 643-646. 4288664. (2007 15th International Conference on Digital Signal Processing, DSP 2007). https://doi.org/10.1109/ICDSP.2007.4288664
Rasetshwane, Daniel M. ; Boston, J. Robert ; Li, Ching Chung. / Use of the articulation index to design a wavelet packet-based method for improving speech intelligibility. 2007 15th International Conference on Digital Signal Processing, DSP 2007. 2007. pp. 643-646 (2007 15th International Conference on Digital Signal Processing, DSP 2007).
@inproceedings{49ce248a9556456c8281059bc26894d4,
title = "Use of the articulation index to design a wavelet packet-based method for improving speech intelligibility",
abstract = "Speech transients are important cues for identifying and discriminating speech sounds, and several studies have suggested that selective amplification of these transients can improve the intelligibility of speech in noise. This paper describes an improved version of a wavelet-based method for extracting transient speech that we described in [9] and the use of the articulation index to select optimal parameters for the method. The new method combines subband decomposition by wavelet packets and transition rate characterization based on the first derivative of short-time energy. The method also incorporates a threshold which, when varied, controls the amount of quasi-steady-state activity that is included in the transient speech signal. The speech modification scheme is optimized and intelligibility improvement is estimated using the articulation index.",
keywords = "Articulation index, Speech enhancement, Transient speech",
author = "Rasetshwane, {Daniel M.} and Boston, {J. Robert} and Li, {Ching Chung}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICDSP.2007.4288664",
language = "English (US)",
isbn = "1424408822",
series = "2007 15th International Conference on Digital Signal Processing, DSP 2007",
pages = "643--646",
booktitle = "2007 15th International Conference on Digital Signal Processing, DSP 2007",

}

TY - GEN

T1 - Use of the articulation index to design a wavelet packet-based method for improving speech intelligibility

AU - Rasetshwane, Daniel M.

AU - Boston, J. Robert

AU - Li, Ching Chung

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Speech transients are important cues for identifying and discriminating speech sounds, and several studies have suggested that selective amplification of these transients can improve the intelligibility of speech in noise. This paper describes an improved version of a wavelet-based method for extracting transient speech that we described in [9] and the use of the articulation index to select optimal parameters for the method. The new method combines subband decomposition by wavelet packets and transition rate characterization based on the first derivative of short-time energy. The method also incorporates a threshold which, when varied, controls the amount of quasi-steady-state activity that is included in the transient speech signal. The speech modification scheme is optimized and intelligibility improvement is estimated using the articulation index.

AB - Speech transients are important cues for identifying and discriminating speech sounds, and several studies have suggested that selective amplification of these transients can improve the intelligibility of speech in noise. This paper describes an improved version of a wavelet-based method for extracting transient speech that we described in [9] and the use of the articulation index to select optimal parameters for the method. The new method combines subband decomposition by wavelet packets and transition rate characterization based on the first derivative of short-time energy. The method also incorporates a threshold which, when varied, controls the amount of quasi-steady-state activity that is included in the transient speech signal. The speech modification scheme is optimized and intelligibility improvement is estimated using the articulation index.

KW - Articulation index

KW - Speech enhancement

KW - Transient speech

UR - http://www.scopus.com/inward/record.url?scp=47649114655&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47649114655&partnerID=8YFLogxK

U2 - 10.1109/ICDSP.2007.4288664

DO - 10.1109/ICDSP.2007.4288664

M3 - Conference contribution

AN - SCOPUS:47649114655

SN - 1424408822

SN - 9781424408825

T3 - 2007 15th International Conference on Digital Signal Processing, DSP 2007

SP - 643

EP - 646

BT - 2007 15th International Conference on Digital Signal Processing, DSP 2007

ER -