CONF BenMahmoud_VIHAR_2024/IDIAP Feature Representations for Automatic Meerkat Vocalization Classification Ben Mahmoud, Imen Sarkar, Eklavya Manser, Marta Magimai-Doss, Mathew bioacoustics call type classification feature representations self-supervised learning EXTERNAL https://publications.idiap.ch/attachments/papers/2024/BenMahmoud_VIHAR_2024.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/BenMahmoud_Idiap-RR-06-2024 Related documents 4th International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots 2024 Understanding evolution of vocal communication in social animals is an important research problem. In that context, beyond humans, there is an interest in analyzing vocalizations of other social animals such as, meerkats, marmosets, apes. While existing approaches address vocalizations of certain species, a reliable method tailored for meerkat calls is lacking. To that extent, this paper investigates feature representations for automatic meerkat vocalization analysis. Both traditional signal processing-based representations and data-driven representations facilitated by advances in deep learning are explored. Call type classification studies conducted on two data sets reveal that feature extraction methods developed for human speech processing can be effectively employed for automatic meerkat call analysis. REPORT BenMahmoud_Idiap-RR-06-2024/IDIAP Feature Representations for Automatic Meerkat Vocalization Classification Ben Mahmoud, Imen Sarkar, Eklavya Manser, Marta Magimai-Doss, Mathew EXTERNAL https://publications.idiap.ch/attachments/reports/2024/BenMahmoud_Idiap-RR-06-2024.pdf PUBLIC Idiap-RR-06-2024 2024 Idiap August 2024 Understanding the evolution of vocal communication in social animals is an important research problem. In that context, beyond humans, there is an interest in analyzing vocalizations of other social animals such as, meerkats, marmosets, apes. While existing approaches address vocalizations of certain species, a reliable method tailored for meerkat calls is lacking. To that extent, this paper investigates feature representations for automatic meerkat vocalization analysis. Both traditional signal processing-based representations and data-driven representations facilitated by advances in deep learning are explored. Call type classification studies conducted on two data sets reveal that feature extraction methods developed for human speech processing can be effectively employed for automatic meerkat call analysis.