Phonetic and Lexical Discovery of Canine Vocalization

Theron S. Wang, Xingyuan Li, Chunhao Zhang, Mengyue Wu, Kenny Q. 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:
10.18653/v1/2024.findings-emnlp.816
Bibkey:
Cite (ACL):
Theron S. Wang, Xingyuan Li, Chunhao Zhang, Mengyue Wu, and Kenny Q. 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