Theron S. Wang, Xingyuan Li, Hridayesh Lekhak, Tuan Minh Dang, Mengyue Wu, Kenny Q. Zhu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

This study centers on the creation of a novel dog bark emotion dataset, EmotionalCanines, capturing the emotional spectrum of canine vocalizations. In the current literature on animal communication and its intersection with machine learning, there is a limited amount of open-sourced data available to facilitate research, mainly due to constraints in animal subjects and recording conditions. To address this gap, we propose a framework that enables the collection of reliable arousal and valence labels in animal emotional state at scale. Through its application, we built a dataset of 1,400 dog bark sequences with corresponding arousal and valence labels, the largest of its kind, for the Husky and Shiba Inu dog breeds. By constructing this dataset, we provide a foundation for decoding dog bark patterns and advancing animal communication research.

Longitudinal studies of animal vocalizations provide crucial insights into developmental patterns and communicative evolution. To aid such investigations in canines, this paper introduces the Canine Age Transition Vocalization Dataset, a large-scale collection of dog vocalizations featuring meticulously verified metadata (including precise birthdate, breed, and individual dog ID) for 125 dogs across 6 common breeds. Our in-depth longitudinal analysis of this dataset then reveals novel findings on how key vocal parameters, encompassing defined bark types and finer-grained acoustic components (Elemental Dog Bark Units, or EDBUs), change as dogs mature. This work, therefore, offers both a significant new resource and foundational data that enable deeper, more nuanced investigations into the lifelong vocal development of dogs and other animal communication.

Progress in understanding real-world canine vocal communication is constrained by datasets lacking scale and 'in-the-wild' diversity. We introduce DogSpeak, a large-scale public dataset of 77,202 Barkseqs (33.162 hours) from 156 dogs (5 breeds), uniquely sourced from online social media with accurate dog ID, sex, and breed labels. DogSpeak, one of the largest of its kind, addresses prior limitations. Benchmark tasks (sex, breed, individual dog recognition) demonstrate its utility and highlight how its inherent real-world challenges necessitate and foster research into more robust bioacoustic models, preprocessing, and feature representation.