An age adapting electrolarynx – A feasibility study

Pieter Coetzee; Joice Lamfel; David M. Rubin; Vered Aharonson

doi:10.1007/978-3-319-94947-5_86

An age adapting electrolarynx – A feasibility study

Pieter Coetzee
, Joice Lamfel
, David M. Rubin
, Vered Aharonson

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

Abstract

We propose a mathematical model for voice aging that could be used in the design of an age-adapting Electrolarynx. Voice data from public figures, at the ages of 30, 40, 50 and 60 years old, were acquired from a YouTube corpus. The voice processing consisted of an extraction of 70 Mel-Frequency Cepstral Coefficients (MFCCs) and a computation of their statistical features. ANOVA F-tests were used to determine which of these features change with age. Significant differences between age groups were found only for the first 40 MFCCs. The aging model was then constructed using non-linear regression and an averaged quadratic polynomial fit on these coefficients. Model age-adapted voices were reconstructed from the young dataset speakers’ voices and compared to their voices at older ages. The model was validated by the correlation between speakers’ MFCCs at older ages and the model-aged MFCCs. The average correlation results were in the range of 0.62 to 0.93. The results imply that the first 40 MFCCs are more susceptible to age related changes and that the proposed model has the potential to enhance the Electrolarynx by providing age adaptation as the speaker grows older.

Original language	English
Title of host publication	Advances in Usability, User Experience and Assistive Technology - Proceedings of the AHFE 2018 International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018
Editors	Christianne Falcao, Tareq Z. Ahram
Publisher	Springer Verlag
Pages	880-886
Number of pages	7
ISBN (Print)	9783319949468
DOIs	https://doi.org/10.1007/978-3-319-94947-5_86
Publication status	Published - 2019
Externally published	Yes
Event	AHFE International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018 - Orlando, United States Duration: 21 Jul 2018 → 25 Jul 2018

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	794
ISSN (Print)	2194-5357

Conference

Conference	AHFE International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018
Country/Territory	United States
City	Orlando
Period	21/07/18 → 25/07/18

Keywords

Electrolarynx
Human factors
Speech processing

Access to Document

10.1007/978-3-319-94947-5_86

Cite this

Coetzee, P., Lamfel, J., Rubin, D. M., & Aharonson, V. (2019). An age adapting electrolarynx – A feasibility study. In C. Falcao, & T. Z. Ahram (Eds.), Advances in Usability, User Experience and Assistive Technology - Proceedings of the AHFE 2018 International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018 (pp. 880-886). (Advances in Intelligent Systems and Computing; Vol. 794). Springer Verlag. https://doi.org/10.1007/978-3-319-94947-5_86

Coetzee, Pieter ; Lamfel, Joice ; Rubin, David M. et al. / An age adapting electrolarynx – A feasibility study. Advances in Usability, User Experience and Assistive Technology - Proceedings of the AHFE 2018 International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018. editor / Christianne Falcao ; Tareq Z. Ahram. Springer Verlag, 2019. pp. 880-886 (Advances in Intelligent Systems and Computing).

@inproceedings{7e05e16e6a294f88a1291d83fbdfe5e0,

title = "An age adapting electrolarynx – A feasibility study",

abstract = "We propose a mathematical model for voice aging that could be used in the design of an age-adapting Electrolarynx. Voice data from public figures, at the ages of 30, 40, 50 and 60 years old, were acquired from a YouTube corpus. The voice processing consisted of an extraction of 70 Mel-Frequency Cepstral Coefficients (MFCCs) and a computation of their statistical features. ANOVA F-tests were used to determine which of these features change with age. Significant differences between age groups were found only for the first 40 MFCCs. The aging model was then constructed using non-linear regression and an averaged quadratic polynomial fit on these coefficients. Model age-adapted voices were reconstructed from the young dataset speakers{\textquoteright} voices and compared to their voices at older ages. The model was validated by the correlation between speakers{\textquoteright} MFCCs at older ages and the model-aged MFCCs. The average correlation results were in the range of 0.62 to 0.93. The results imply that the first 40 MFCCs are more susceptible to age related changes and that the proposed model has the potential to enhance the Electrolarynx by providing age adaptation as the speaker grows older.",

keywords = "Electrolarynx, Human factors, Speech processing",

author = "Pieter Coetzee and Joice Lamfel and Rubin, \{David M.\} and Vered Aharonson",

note = "Publisher Copyright: {\textcopyright} 2019, Springer International Publishing AG, part of Springer Nature.; AHFE International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018 ; Conference date: 21-07-2018 Through 25-07-2018",

year = "2019",

doi = "10.1007/978-3-319-94947-5\_86",

language = "English",

isbn = "9783319949468",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "880--886",

editor = "Christianne Falcao and Ahram, \{Tareq Z.\}",

booktitle = "Advances in Usability, User Experience and Assistive Technology - Proceedings of the AHFE 2018 International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018",

}

Coetzee, P, Lamfel, J, Rubin, DM & Aharonson, V 2019, An age adapting electrolarynx – A feasibility study. in C Falcao & TZ Ahram (eds), Advances in Usability, User Experience and Assistive Technology - Proceedings of the AHFE 2018 International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018. Advances in Intelligent Systems and Computing, vol. 794, Springer Verlag, pp. 880-886, AHFE International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018, Orlando, United States, 21/07/18. https://doi.org/10.1007/978-3-319-94947-5_86

An age adapting electrolarynx – A feasibility study. / Coetzee, Pieter; Lamfel, Joice; Rubin, David M. et al.
Advances in Usability, User Experience and Assistive Technology - Proceedings of the AHFE 2018 International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018. ed. / Christianne Falcao; Tareq Z. Ahram. Springer Verlag, 2019. p. 880-886 (Advances in Intelligent Systems and Computing; Vol. 794).

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

TY - GEN

T1 - An age adapting electrolarynx – A feasibility study

AU - Coetzee, Pieter

AU - Lamfel, Joice

AU - Rubin, David M.

AU - Aharonson, Vered

PY - 2019

Y1 - 2019

N2 - We propose a mathematical model for voice aging that could be used in the design of an age-adapting Electrolarynx. Voice data from public figures, at the ages of 30, 40, 50 and 60 years old, were acquired from a YouTube corpus. The voice processing consisted of an extraction of 70 Mel-Frequency Cepstral Coefficients (MFCCs) and a computation of their statistical features. ANOVA F-tests were used to determine which of these features change with age. Significant differences between age groups were found only for the first 40 MFCCs. The aging model was then constructed using non-linear regression and an averaged quadratic polynomial fit on these coefficients. Model age-adapted voices were reconstructed from the young dataset speakers’ voices and compared to their voices at older ages. The model was validated by the correlation between speakers’ MFCCs at older ages and the model-aged MFCCs. The average correlation results were in the range of 0.62 to 0.93. The results imply that the first 40 MFCCs are more susceptible to age related changes and that the proposed model has the potential to enhance the Electrolarynx by providing age adaptation as the speaker grows older.

AB - We propose a mathematical model for voice aging that could be used in the design of an age-adapting Electrolarynx. Voice data from public figures, at the ages of 30, 40, 50 and 60 years old, were acquired from a YouTube corpus. The voice processing consisted of an extraction of 70 Mel-Frequency Cepstral Coefficients (MFCCs) and a computation of their statistical features. ANOVA F-tests were used to determine which of these features change with age. Significant differences between age groups were found only for the first 40 MFCCs. The aging model was then constructed using non-linear regression and an averaged quadratic polynomial fit on these coefficients. Model age-adapted voices were reconstructed from the young dataset speakers’ voices and compared to their voices at older ages. The model was validated by the correlation between speakers’ MFCCs at older ages and the model-aged MFCCs. The average correlation results were in the range of 0.62 to 0.93. The results imply that the first 40 MFCCs are more susceptible to age related changes and that the proposed model has the potential to enhance the Electrolarynx by providing age adaptation as the speaker grows older.

KW - Electrolarynx

KW - Human factors

KW - Speech processing

UR - https://www.scopus.com/pages/publications/85049531898

U2 - 10.1007/978-3-319-94947-5_86

DO - 10.1007/978-3-319-94947-5_86

M3 - Conference contribution

AN - SCOPUS:85049531898

SN - 9783319949468

T3 - Advances in Intelligent Systems and Computing

SP - 880

EP - 886

BT - Advances in Usability, User Experience and Assistive Technology - Proceedings of the AHFE 2018 International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018

A2 - Falcao, Christianne

A2 - Ahram, Tareq Z.

PB - Springer Verlag

T2 - AHFE International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018

Y2 - 21 July 2018 through 25 July 2018

ER -

Coetzee P, Lamfel J, Rubin DM, Aharonson V. An age adapting electrolarynx – A feasibility study. In Falcao C, Ahram TZ, editors, Advances in Usability, User Experience and Assistive Technology - Proceedings of the AHFE 2018 International Conferences on Usability and User Experience and Human Factors and Assistive Technology, 2018. Springer Verlag. 2019. p. 880-886. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-319-94947-5_86

An age adapting electrolarynx – A feasibility study

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this