Towards Dog Bark Decoding: Leveraging Human Speech Processing for Automated Bark Classification
This work addresses automated classification of dog vocalizations, which is an incremental domain-specific problem for animal behavior research and pet technology applications.
The paper tackled dog bark classification tasks including dog recognition, breed identification, gender classification, and context grounding by leveraging self-supervised speech representation models pre-trained on human speech, showing significant improvements over simpler baselines and additional performance boosts from human speech pre-training.
Similar to humans, animals make extensive use of verbal and non-verbal forms of communication, including a large range of audio signals. In this paper, we address dog vocalizations and explore the use of self-supervised speech representation models pre-trained on human speech to address dog bark classification tasks that find parallels in human-centered tasks in speech recognition. We specifically address four tasks: dog recognition, breed identification, gender classification, and context grounding. We show that using speech embedding representations significantly improves over simpler classification baselines. Further, we also find that models pre-trained on large human speech acoustics can provide additional performance boosts on several tasks.