Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech

Sudarsana Reddy Kadiri; Paavo Alku

doi:10.21437/Interspeech.2019-2863

Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech

Sudarsana Reddy Kadiri, Paavo Alku

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

4 Citations (Scopus)

99 Downloads (Pure)

Abstract

Voice source characteristics in different phonation types vary due to the tension of laryngeal muscles along with the respiratory effort. This study investigates the use of mel-frequency cepstral coefficients (MFCCs) derived from voice source waveforms for classification of phonation types in speech. The cepstral coefficients are computed using two source waveforms: (1) glottal flow waveforms estimated by the quasi-closed phase (QCP) glottal inverse filtering method and (2) approximate voice source waveforms obtained using the zero frequency filtering (ZFF) method. QCP estimates voice source waveforms based on the source-filter decomposition while ZFF yields source waveforms without explicitly computing the source-filter decomposition. Experiments using MFCCs computed from the two source waveforms show improved accuracy in classification of phonation types compared to the existing voice source features and conventional MFCC features. Further, it is observed that the proposed features have complimentary information to the existing features.

Original language	English
Title of host publication	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publisher	International Speech Communication Association
Pages	2508-2512
Number of pages	5
Volume	2019-September
DOIs	https://doi.org/10.21437/Interspeech.2019-2863
Publication status	Published - 1 Jan 2019
MoE publication type	A4 Article in a conference publication
Event	Interspeech - Graz, Austria Duration: 15 Sep 2019 → 19 Sep 2019 https://www.interspeech2019.org/

Publication series

Name	Interspeech - Annual Conference of the International Speech Communication Association, INTERSPEECH
ISSN (Electronic)	2308-457X

Conference

Conference	Interspeech
Country	Austria
City	Graz
Period	15/09/2019 → 19/09/2019
Internet address	https://www.interspeech2019.org/

Keywords

Glottal inverse filtering
Phonation type
Speech analysis
Voice quality
Voice source
Zero frequency filtering

Access to Document

10.21437/Interspeech.2019-2863

ELEC_Kadiri_Mel-frequency_cepstral_INTERSPEECHFinal published version, 700 KB

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech'. Together they form a unique fingerprint.

1 Finished

Interdisciplinary research on statistical parametric speech synthesis
Juvela, L., Airaksinen, M., Bäckström, T. & Alku, P.
01/01/2018 → 31/12/2019
Project: Academy of Finland: Other research funding

Cite this

Kadiri, S. R., & Alku, P. (2019). Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH (Vol. 2019-September, pp. 2508-2512). (Interspeech - Annual Conference of the International Speech Communication Association, INTERSPEECH). International Speech Communication Association. https://doi.org/10.21437/Interspeech.2019-2863

Kadiri, Sudarsana Reddy ; Alku, Paavo. / Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2019-September International Speech Communication Association, 2019. pp. 2508-2512 (Interspeech - Annual Conference of the International Speech Communication Association, INTERSPEECH).

@inproceedings{d512c3fbcf234209b0109bcb51febe3a,

title = "Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech",

abstract = "Voice source characteristics in different phonation types vary due to the tension of laryngeal muscles along with the respiratory effort. This study investigates the use of mel-frequency cepstral coefficients (MFCCs) derived from voice source waveforms for classification of phonation types in speech. The cepstral coefficients are computed using two source waveforms: (1) glottal flow waveforms estimated by the quasi-closed phase (QCP) glottal inverse filtering method and (2) approximate voice source waveforms obtained using the zero frequency filtering (ZFF) method. QCP estimates voice source waveforms based on the source-filter decomposition while ZFF yields source waveforms without explicitly computing the source-filter decomposition. Experiments using MFCCs computed from the two source waveforms show improved accuracy in classification of phonation types compared to the existing voice source features and conventional MFCC features. Further, it is observed that the proposed features have complimentary information to the existing features.",

keywords = "Glottal inverse filtering, Phonation type, Speech analysis, Voice quality, Voice source, Zero frequency filtering",

author = "Kadiri, {Sudarsana Reddy} and Paavo Alku",

year = "2019",

month = jan,

day = "1",

doi = "10.21437/Interspeech.2019-2863",

language = "English",

volume = "2019-September",

series = "Interspeech - Annual Conference of the International Speech Communication Association, INTERSPEECH",

publisher = "International Speech Communication Association",

pages = "2508--2512",

booktitle = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

note = "Interspeech ; Conference date: 15-09-2019 Through 19-09-2019",

url = "https://www.interspeech2019.org/",

}

Kadiri, SR & Alku, P 2019, Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech. in Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. vol. 2019-September, Interspeech - Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association, pp. 2508-2512, Interspeech, Graz, Austria, 15/09/2019. https://doi.org/10.21437/Interspeech.2019-2863

Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech. / Kadiri, Sudarsana Reddy ; Alku, Paavo.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2019-September International Speech Communication Association, 2019. p. 2508-2512 (Interspeech - Annual Conference of the International Speech Communication Association, INTERSPEECH).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech

AU - Kadiri, Sudarsana Reddy

AU - Alku, Paavo

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Voice source characteristics in different phonation types vary due to the tension of laryngeal muscles along with the respiratory effort. This study investigates the use of mel-frequency cepstral coefficients (MFCCs) derived from voice source waveforms for classification of phonation types in speech. The cepstral coefficients are computed using two source waveforms: (1) glottal flow waveforms estimated by the quasi-closed phase (QCP) glottal inverse filtering method and (2) approximate voice source waveforms obtained using the zero frequency filtering (ZFF) method. QCP estimates voice source waveforms based on the source-filter decomposition while ZFF yields source waveforms without explicitly computing the source-filter decomposition. Experiments using MFCCs computed from the two source waveforms show improved accuracy in classification of phonation types compared to the existing voice source features and conventional MFCC features. Further, it is observed that the proposed features have complimentary information to the existing features.

AB - Voice source characteristics in different phonation types vary due to the tension of laryngeal muscles along with the respiratory effort. This study investigates the use of mel-frequency cepstral coefficients (MFCCs) derived from voice source waveforms for classification of phonation types in speech. The cepstral coefficients are computed using two source waveforms: (1) glottal flow waveforms estimated by the quasi-closed phase (QCP) glottal inverse filtering method and (2) approximate voice source waveforms obtained using the zero frequency filtering (ZFF) method. QCP estimates voice source waveforms based on the source-filter decomposition while ZFF yields source waveforms without explicitly computing the source-filter decomposition. Experiments using MFCCs computed from the two source waveforms show improved accuracy in classification of phonation types compared to the existing voice source features and conventional MFCC features. Further, it is observed that the proposed features have complimentary information to the existing features.

KW - Glottal inverse filtering

KW - Phonation type

KW - Speech analysis

KW - Voice quality

KW - Voice source

KW - Zero frequency filtering

UR - http://www.scopus.com/inward/record.url?scp=85074692228&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2019-2863

DO - 10.21437/Interspeech.2019-2863

M3 - Conference contribution

AN - SCOPUS:85074692228

VL - 2019-September

T3 - Interspeech - Annual Conference of the International Speech Communication Association, INTERSPEECH

SP - 2508

EP - 2512

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

PB - International Speech Communication Association

T2 - Interspeech

Y2 - 15 September 2019 through 19 September 2019

ER -

Kadiri SR , Alku P. Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Vol. 2019-September. International Speech Communication Association. 2019. p. 2508-2512. (Interspeech - Annual Conference of the International Speech Communication Association, INTERSPEECH). https://doi.org/10.21437/Interspeech.2019-2863

Mel-frequency cepstral coefficients of voice source waveforms for classification of phonation types in speech

Abstract

Publication series

Conference

Keywords

Access to Document

Interdisciplinary research on statistical parametric speech synthesis

Cite this