Acoustic barycenters as exemplar production targets

Frederic Mailhot, Cassandra L. Jacobs


Abstract
We present a solution to the problem of exemplar-based language production from variable-duration tokens, leveraging algorithms from the domain of time-series clustering and classification. Our model stores and outputs tokens of phonetically rich and temporally variable representations of recorded speech. We show qualitatively and quantitatively that model outputs retain essential acoustic/phonetic characteristics despite the noise introduced by averaging, and also demonstrate the effects of similarity and indexical information as constraints on exemplar cloud selection.
Anthology ID:
2024.sigmorphon-1.8
Volume:
Proceedings of the 21st SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Garrett Nicolai, Eleanor Chodroff, Frederic Mailhot, Çağrı Çöltekin
Venue:
SIGMORPHON
SIG:
SIGMORPHON
Publisher:
Association for Computational Linguistics
Note:
Pages:
67–76
Language:
URL:
https://aclanthology.org/2024.sigmorphon-1.8
DOI:
10.18653/v1/2024.sigmorphon-1.8
Bibkey:
Cite (ACL):
Frederic Mailhot and Cassandra L. Jacobs. 2024. Acoustic barycenters as exemplar production targets. In Proceedings of the 21st SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 67–76, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Acoustic barycenters as exemplar production targets (Mailhot & Jacobs, SIGMORPHON 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigmorphon-1.8.pdf