Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio

Jung Won Lee, Hong Goo Kang, Samuel Kim, Yoonjae Lee

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

1 Citation (Scopus)

Abstract

This paper proposes an efficient feature extraction method for automatic diagnosis systems to detect pathological subjects using continuous speech. Since continuous speech contains slow and rapid adjustments of vocal mechanisms which relate to initiations and terminations of voicing, the proposed algorithm utilizes both localized temporal characteristics and histogram-based global statistics of harmonic-to-noise ratio (HNR) to efficiently differentiate the key features from phonetic variation. Experimental results show that the proposed method improves the classification error rate by 11.2 % (relative) compared to the conventional method using HNR.

Original languageEnglish
Title of host publication2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013
DOIs
Publication statusPublished - 2013 Dec 1
Event2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 - Kaohsiung, Taiwan, Province of China
Duration: 2013 Oct 292013 Nov 1

Other

Other2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013
CountryTaiwan, Province of China
CityKaohsiung
Period13/10/2913/11/1

Fingerprint

Speech analysis
Feature extraction
Statistics

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Signal Processing

Cite this

Lee, J. W., Kang, H. G., Kim, S., & Lee, Y. (2013). Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio. In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013 [6694115] https://doi.org/10.1109/APSIPA.2013.6694115
Lee, Jung Won ; Kang, Hong Goo ; Kim, Samuel ; Lee, Yoonjae. / Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio. 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013.
@inproceedings{3e37d8a0a79e41a68627007559815348,
title = "Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio",
abstract = "This paper proposes an efficient feature extraction method for automatic diagnosis systems to detect pathological subjects using continuous speech. Since continuous speech contains slow and rapid adjustments of vocal mechanisms which relate to initiations and terminations of voicing, the proposed algorithm utilizes both localized temporal characteristics and histogram-based global statistics of harmonic-to-noise ratio (HNR) to efficiently differentiate the key features from phonetic variation. Experimental results show that the proposed method improves the classification error rate by 11.2 {\%} (relative) compared to the conventional method using HNR.",
author = "Lee, {Jung Won} and Kang, {Hong Goo} and Samuel Kim and Yoonjae Lee",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/APSIPA.2013.6694115",
language = "English",
isbn = "9789869000604",
booktitle = "2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013",

}

Lee, JW, Kang, HG, Kim, S & Lee, Y 2013, Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio. in 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013., 6694115, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013, Kaohsiung, Taiwan, Province of China, 13/10/29. https://doi.org/10.1109/APSIPA.2013.6694115

Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio. / Lee, Jung Won; Kang, Hong Goo; Kim, Samuel; Lee, Yoonjae.

2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013. 6694115.

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

TY - GEN

T1 - Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio

AU - Lee, Jung Won

AU - Kang, Hong Goo

AU - Kim, Samuel

AU - Lee, Yoonjae

PY - 2013/12/1

Y1 - 2013/12/1

N2 - This paper proposes an efficient feature extraction method for automatic diagnosis systems to detect pathological subjects using continuous speech. Since continuous speech contains slow and rapid adjustments of vocal mechanisms which relate to initiations and terminations of voicing, the proposed algorithm utilizes both localized temporal characteristics and histogram-based global statistics of harmonic-to-noise ratio (HNR) to efficiently differentiate the key features from phonetic variation. Experimental results show that the proposed method improves the classification error rate by 11.2 % (relative) compared to the conventional method using HNR.

AB - This paper proposes an efficient feature extraction method for automatic diagnosis systems to detect pathological subjects using continuous speech. Since continuous speech contains slow and rapid adjustments of vocal mechanisms which relate to initiations and terminations of voicing, the proposed algorithm utilizes both localized temporal characteristics and histogram-based global statistics of harmonic-to-noise ratio (HNR) to efficiently differentiate the key features from phonetic variation. Experimental results show that the proposed method improves the classification error rate by 11.2 % (relative) compared to the conventional method using HNR.

UR - http://www.scopus.com/inward/record.url?scp=84893317850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893317850&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2013.6694115

DO - 10.1109/APSIPA.2013.6694115

M3 - Conference contribution

SN - 9789869000604

BT - 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013

ER -

Lee JW, Kang HG, Kim S, Lee Y. Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio. In 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2013. 2013. 6694115 https://doi.org/10.1109/APSIPA.2013.6694115