Phonetic and Lexical Discovery of Canine Vocalization

Theron Wang, Xingyuan Li, Chunhao Zhang, Mengyue Wu, Kenny Zhu


Abstract
This paper attempts to discover communication patterns automatically within dog vocalizations in a data-driven approach, which breaks the barrier previous approaches that rely on human prior knowledge on limited data. We present a self-supervised approach with HuBERT, enabling the accurate classification of phones, and an adaptive grammar induction method that identifies phone sequence patterns that suggest a preliminary vocabulary within dog vocalizations. Our results show that a subset of this vocabulary has substantial causality relations with certain canine activities, suggesting signs of stable semantics associated with these “words”.
Anthology ID:
2024.findings-emnlp.816
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13972–13983
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.816
DOI:
Bibkey:
Cite (ACL):
Theron Wang, Xingyuan Li, Chunhao Zhang, Mengyue Wu, and Kenny Zhu. 2024. Phonetic and Lexical Discovery of Canine Vocalization. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 13972–13983, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Phonetic and Lexical Discovery of Canine Vocalization (Wang et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.816.pdf