publications | Theron S. Wang

2026

Unsupervised Discovery and Analysis of the Vocal Repertoires and Patterns of Select Corvid Species

Nitin Sudarsanam, Sahla Kader, Isaac Fernandezlopez, and 5 more authors

In ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026

@inproceedings{sudarsanam2026unsupervised,
  author = {Sudarsanam, Nitin and Kader, Sahla and Fernandezlopez, Isaac and Huang, Sophie and Dang, Tuan M. and Wang, Theron S. and Lekhak, Hridayesh and Zhu, Kenny Q.},
  title = {Unsupervised Discovery and Analysis of the Vocal Repertoires and Patterns of Select Corvid Species},
  booktitle = {ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year = {2026},
  pages = {15217--15221},
  publisher = {IEEE},
  doi = {10.1109/ICASSP55912.2026.11462057},
}

CSUR
A Preview of Computational Animal Linguistics

Tuan M. Dang, Atrey Desai, Hridayesh Lekhak, and 4 more authors

ACM Computing Surveys, Oct 2026

Abs DOI Bib HTML

Computational animal linguistics is an emerging field that studies non-human animal vocal communication as a language system using data-driven computational approaches. This survey starts with humanity’s historical endeavor to understand animal communication and a background on the essential linguistic properties in human languages. It presents current evidence of animals possessing some of these properties previously thought to be unique to humans. Driven by advancements in deep learning and artificial intelligence, computational methods from natural language processing and large language modeling are playing a major role in processing and understanding animal communication on a larger scale moving forward beyond traditional approaches.
@article{10.1145/3850160, author = {Dang, Tuan M. and Desai, Atrey and Lekhak, Hridayesh and Panunto, Tirza and Pike, Lindsay and Wang, Theron S. and Zhu, Kenny Q.}, title = {A Preview of Computational Animal Linguistics}, journal = {ACM Computing Surveys}, year = {2026}, month = oct, issn = {1557-7341}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3850160}, doi = {10.1145/3850160}, }
arXiv
Audio-Visual Dog Identification and Tracking in Real-World Videos

Aryahvishwa Babu, Kingsley Jin, Lillian Wang, and 5 more authors

arXiv preprint arXiv:2610.21011, Oct 2026

Abs Bib HTML PDF

Identifying individual dogs from barks in real-world videos remains challenging and largely unexplored. Solving this problem would enable long-term behavioral analysis, veterinary monitoring, and animal welfare monitoring by attributing vocalizations and behaviors to the correct individual. Real-world videos are challenging because multiple dogs may bark simultaneously, become occluded, or move in and out of view. Prior studies show that canine vocalizations and visual appearance contain discriminative identity information, but these modalities have largely been studied independently. We present a multimodal dog-fingerprinting framework combining visual identification, multiple-object tracking, and canine vocal fingerprinting to associate bark events with individual dogs while maintaining persistent profiles. The framework synchronizes bark events with tracked dogs and updates profiles using visual appearance and vocal characteristics, enabling identification despite occlusion, overlapping vocalizations, and off-screen barking. We also introduce a benchmark of 46 real-world videos containing 213 manually annotated bark events. Our framework correctly localizes the active visible dog in 61.83% of visible events at IoU ≥ 0.30 and achieves a 91.33% F1 score for visible versus off-screen barking detection.
@article{babu2026audiovisual, title = {Audio-Visual Dog Identification and Tracking in Real-World Videos}, author = {Babu, Aryahvishwa and Jin, Kingsley and Wang, Lillian and Dang, Tuan M. and Wang, Theron S. and Joshi, Jeorge and Cao, Annie and Zhu, Kenny Q.}, journal = {arXiv preprint arXiv:2610.21011}, year = {2026}, month = oct, }

2025

ACL
Toward Automatic Discovery of a Canine Phonetic Alphabet

Theron S. Wang, Xingyuan Li, Hridayesh Lekhak, and 3 more authors

In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2025

Outstanding Paper Award Abs DOI Bib HTML PDF

Outstanding Paper Award

Dogs communicate intelligently but little is known about the phonetic properties of their vocalization communication. For the first time, this paper presents an iterative algorithm inspired by human phonetic discovery, which is based on minimal pairs that determine phonemes by distinguishing different words in human language, and is able to produce a complete alphabet of distinct canine phoneme-like units. In addition, the algorithm produces a number of canine repeated acoustic units, which may correspond to specific environments and activities of a dog, composed exclusively of the canine phoneme-like units in the alphabet. The framework outlined in this paper is expected to function not only on canines but other animal species.
@inproceedings{wang-etal-2025-toward, title = {Toward Automatic Discovery of a Canine Phonetic Alphabet}, author = {Wang, Theron S. and Li, Xingyuan and Lekhak, Hridayesh and Dang, Tuan Minh and Wu, Mengyue and Zhu, Kenny Q.}, editor = {Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher}, booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, month = jul, year = {2025}, address = {Vienna, Austria}, publisher = {Association for Computational Linguistics}, url = {https://aclanthology.org/2025.acl-long.451/}, doi = {10.18653/v1/2025.acl-long.451}, pages = {9207--9219}, isbn = {979-8-89176-251-0}, selected = true, }
ACM MM
DogSpeak: A Canine Vocalization Classification Dataset

Hridayesh Lekhak, Theron S. Wang, Tuan M. Dang, and 1 more author

In Proceedings of the 33rd ACM International Conference on Multimedia, Dublin, Ireland, Jul 2025

Abs DOI Bib

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.
@inproceedings{10.1145/3746027.3758298, author = {Lekhak, Hridayesh and Wang, Theron S. and Dang, Tuan M. and Zhu, Kenny Q.}, title = {DogSpeak: A Canine Vocalization Classification Dataset}, year = {2025}, isbn = {9798400720352}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3746027.3758298}, doi = {10.1145/3746027.3758298}, booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia}, pages = {13369–13375}, numpages = {7}, keywords = {animal communication, bioacoustics classification, canine vocalization, computational bioacoustics, dog bark analysis, machine learning, vocalization dataset}, location = {Dublin, Ireland}, series = {MM '25}, }
ACM MM
EmotionalCanines: A Dataset for Analysis of Arousal and Valence in Dog Vocalization

Tuan M. Dang, Theron S. Wang, Hridayesh Lekhak, and 1 more author

In Proceedings of the 33rd ACM International Conference on Multimedia, Dublin, Ireland, Jul 2025

Abs DOI Bib

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.
@inproceedings{10.1145/3746027.3758286, author = {Dang, Tuan M. and Wang, Theron S. and Lekhak, Hridayesh and Zhu, Kenny Q.}, title = {EmotionalCanines: A Dataset for Analysis of Arousal and Valence in Dog Vocalization}, year = {2025}, isbn = {9798400720352}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3746027.3758286}, doi = {10.1145/3746027.3758286}, booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia}, pages = {13281–13288}, numpages = {8}, keywords = {animal communication, animal emotions, bioacoustics, dogs}, location = {Dublin, Ireland}, series = {MM '25}, }
ACM MM
A Data-driven Approach to the Longitudinal Study of Canine Vocal Pattern Development

Hridayesh Lekhak, Tuan M. Dang, Theron S. Wang, and 1 more author

In Proceedings of the 33rd ACM International Conference on Multimedia, Dublin, Ireland, Jul 2025

Abs DOI Bib

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.
@inproceedings{10.1145/3746027.3758175, author = {Lekhak, Hridayesh and Dang, Tuan M. and Wang, Theron S. and Zhu, Kenny Q.}, title = {A Data-driven Approach to the Longitudinal Study of Canine Vocal Pattern Development}, year = {2025}, isbn = {9798400720352}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3746027.3758175}, doi = {10.1145/3746027.3758175}, booktitle = {Proceedings of the 33rd ACM International Conference on Multimedia}, pages = {12473–12482}, numpages = {10}, keywords = {age-related vocal development, animal communication, bioacoustic classification, bioacoustics, canine vocalization dataset, longitudinal study, machine learning}, location = {Dublin, Ireland}, series = {MM '25}, }

2024

EMNLP
Phonetic and Lexical Discovery of Canine Vocalization

Theron S. Wang, Xingyuan Li, Chunhao Zhang, and 2 more authors

In Findings of the Association for Computational Linguistics: EMNLP 2024, Nov 2024

Abs Bib HTML PDF

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”.
@inproceedings{wang-etal-2024-phonetic, title = {Phonetic and Lexical Discovery of Canine Vocalization}, author = {Wang, Theron S. and Li, Xingyuan and Zhang, Chunhao and Wu, Mengyue and Zhu, Kenny Q.}, editor = {Al-Onaizan, Yaser and Bansal, Mohit and Chen, Yun-Nung}, booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2024}, month = nov, year = {2024}, address = {Miami, Florida, USA}, publisher = {Association for Computational Linguistics}, url = {https://aclanthology.org/2024.findings-emnlp.816}, pages = {13972--13983}, selected = true, }
arXiv
Phonetic and Lexical Discovery of a Canine Language using HuBERT

Xingyuan Li, Sinong Wang, Zeyu Xie, and 2 more authors

arXiv preprint arXiv:2402.15985, Nov 2024

Abs Bib HTML PDF

This paper delves into the pioneering exploration of potential communication patterns within dog vocalizations and transcends traditional linguistic analysis barriers, which heavily relies on human priori knowledge on limited datasets to find sound units in dog vocalization. We present a self-supervised approach with HuBERT, enabling the accurate classification of phoneme labels and the identification of vocal patterns that suggest a rudimentary vocabulary within dog vocalizations. Our findings indicate a significant acoustic consistency in these identified canine vocabulary, covering the entirety of observed dog vocalization sequences. We further develop a web-based dog vocalization labeling system. This system can highlight phoneme n-grams, present in the vocabulary, in the dog audio uploaded by users.
@article{li2024phonetic, title = {Phonetic and Lexical Discovery of a Canine Language using HuBERT}, author = {Li, Xingyuan and Wang, Sinong and Xie, Zeyu and Wu, Mengyue and Zhu, Kenny Q}, journal = {arXiv preprint arXiv:2402.15985}, year = {2024}, }