The Role of Prosody and Speech Register in Word Segmentation: A Computational Modelling Perspective

Bogdan Ludusan, Reiko Mazuka, Mathieu Bernard, Alejandrina Cristia, Emmanuel Dupoux


Abstract
This study explores the role of speech register and prosody for the task of word segmentation. Since these two factors are thought to play an important role in early language acquisition, we aim to quantify their contribution for this task. We study a Japanese corpus containing both infant- and adult-directed speech and we apply four different word segmentation models, with and without knowledge of prosodic boundaries. The results showed that the difference between registers is smaller than previously reported and that prosodic boundary information helps more adult- than infant-directed speech.
Anthology ID:
P17-2028
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
178–183
Language:
URL:
https://aclanthology.org/P17-2028
DOI:
10.18653/v1/P17-2028
Bibkey:
Cite (ACL):
Bogdan Ludusan, Reiko Mazuka, Mathieu Bernard, Alejandrina Cristia, and Emmanuel Dupoux. 2017. The Role of Prosody and Speech Register in Word Segmentation: A Computational Modelling Perspective. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 178–183, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
The Role of Prosody and Speech Register in Word Segmentation: A Computational Modelling Perspective (Ludusan et al., ACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/P17-2028.pdf
Video:
 https://aclanthology.org/P17-2028.mp4