Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis

Daniel R. van Niekerk; Anqi Xu; Branislav Gerazov; Paul K. Krug; Peter Birkholz; Yi Xu

doi:10.21437/Interspeech.2020-2545

Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis

Daniel R. van Niekerk^*
, Anqi Xu
, Branislav Gerazov
, Paul K. Krug
, Peter Birkholz
, Yi Xu

^*Corresponding author for this work

University College London
SS Cyril and Methodius University in Skopje
Technische Universität Dresden

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

5 Scopus citations

Abstract

In this study, a state-of-the-art articulatory speech synthesiser was used as the basis for simulating the exploration of CV sounds imitating speech stimuli. By adopting a relevant kinematic model and systematically reducing the search space of consonant articulatory targets, intelligible CV sounds can be found. Derivative-free optimisation strategies were evaluated to speed up the process of exploring articulatory space and the possibility of using automatic speech recognition as a means of evaluating intelligibility was explored.

Original language	English
Title of host publication	Interspeech 2020
Publisher	International Speech Communication Association
Pages	4457-4461
Number of pages	5
ISBN (Print)	9781713820697
DOIs	https://doi.org/10.21437/Interspeech.2020-2545
State	Published - 2020
Externally published	Yes
Event	21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 - Shanghai, China Duration: 25 Oct 2020 → 29 Oct 2020

Publication series

Name	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	2020-October
ISSN (Print)	2308-457X
ISSN (Electronic)	1990-9772

Conference

Conference	21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020
Country/Territory	China
City	Shanghai
Period	25/10/20 → 29/10/20

Keywords

Articulatory speech synthesis
Computational phonetics
Early vocal learning

Access to Document

10.21437/Interspeech.2020-2545

Cite this

van Niekerk, D. R., Xu, A., Gerazov, B., Krug, P. K., Birkholz, P., & Xu, Y. (2020). Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis. In Interspeech 2020 (pp. 4457-4461). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 2020-October). International Speech Communication Association. https://doi.org/10.21437/Interspeech.2020-2545

@inproceedings{924af9f0b8304d9bad3598f60f469ac9,

title = "Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis",

abstract = "In this study, a state-of-the-art articulatory speech synthesiser was used as the basis for simulating the exploration of CV sounds imitating speech stimuli. By adopting a relevant kinematic model and systematically reducing the search space of consonant articulatory targets, intelligible CV sounds can be found. Derivative-free optimisation strategies were evaluated to speed up the process of exploring articulatory space and the possibility of using automatic speech recognition as a means of evaluating intelligibility was explored.",

keywords = "Articulatory speech synthesis, Computational phonetics, Early vocal learning",

author = "\{van Niekerk\}, \{Daniel R.\} and Anqi Xu and Branislav Gerazov and Krug, \{Paul K.\} and Peter Birkholz and Yi Xu",

note = "Publisher Copyright: Copyright {\textcopyright} 2020 ISCA; 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020 ; Conference date: 25-10-2020 Through 29-10-2020",

year = "2020",

doi = "10.21437/Interspeech.2020-2545",

language = "英语",

isbn = "9781713820697",

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

publisher = "International Speech Communication Association",

pages = "4457--4461",

booktitle = "Interspeech 2020",

address = "法国",

}

van Niekerk, DR, Xu, A, Gerazov, B, Krug, PK, Birkholz, P & Xu, Y 2020, Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis. in Interspeech 2020. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, vol. 2020-October, International Speech Communication Association, pp. 4457-4461, 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020, Shanghai, China, 25/10/20. https://doi.org/10.21437/Interspeech.2020-2545

Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis. / van Niekerk, Daniel R.; Xu, Anqi; Gerazov, Branislav et al.
Interspeech 2020. International Speech Communication Association, 2020. p. 4457-4461 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 2020-October).

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

TY - GEN

T1 - Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis

AU - van Niekerk, Daniel R.

AU - Xu, Anqi

AU - Gerazov, Branislav

AU - Krug, Paul K.

AU - Birkholz, Peter

AU - Xu, Yi

PY - 2020

Y1 - 2020

N2 - In this study, a state-of-the-art articulatory speech synthesiser was used as the basis for simulating the exploration of CV sounds imitating speech stimuli. By adopting a relevant kinematic model and systematically reducing the search space of consonant articulatory targets, intelligible CV sounds can be found. Derivative-free optimisation strategies were evaluated to speed up the process of exploring articulatory space and the possibility of using automatic speech recognition as a means of evaluating intelligibility was explored.

AB - In this study, a state-of-the-art articulatory speech synthesiser was used as the basis for simulating the exploration of CV sounds imitating speech stimuli. By adopting a relevant kinematic model and systematically reducing the search space of consonant articulatory targets, intelligible CV sounds can be found. Derivative-free optimisation strategies were evaluated to speed up the process of exploring articulatory space and the possibility of using automatic speech recognition as a means of evaluating intelligibility was explored.

KW - Articulatory speech synthesis

KW - Computational phonetics

KW - Early vocal learning

UR - https://www.scopus.com/pages/publications/85098214930

U2 - 10.21437/Interspeech.2020-2545

DO - 10.21437/Interspeech.2020-2545

M3 - 会议稿件

AN - SCOPUS:85098214930

SN - 9781713820697

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

SP - 4457

EP - 4461

BT - Interspeech 2020

PB - International Speech Communication Association

T2 - 21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020

Y2 - 25 October 2020 through 29 October 2020

ER -

van Niekerk DR, Xu A, Gerazov B, Krug PK, Birkholz P, Xu Y. Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis. In Interspeech 2020. International Speech Communication Association. 2020. p. 4457-4461. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). doi: 10.21437/Interspeech.2020-2545

Finding intelligible consonant-vowel sounds using high-quality articulatory synthesis

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this