{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/on-the-utility-of-speech-and-audio-foundation","title":"On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis","arxiv_id":"2407.16417","date":"2024-07-23","proceeding":null,"authors":["Eklavya Sarkar","Mathew Magimai. -Doss"],"abstract":"Marmoset monkeys encode vital information in their calls and serve as a surrogate model for neuro-biologists to understand the evolutionary origins of human vocal communication. Traditionally analyzed with signal processing-based features, recent approaches have utilized self-supervised models pre-trained on human speech for feature extraction, capitalizing on their ability to learn a signal's intrinsic structure independently of its acoustic domain. However, the utility of such foundation models remains unclear for marmoset call analysis in terms of multi-class classification, bandwidth, and pre-training domain. This study assesses feature representations derived from speech and general audio domains, across pre-training bandwidths of 4, 8, and 16 kHz for marmoset call-type and caller classification tasks. Results show that models with higher bandwidth improve performance, and pre-training on speech or general audio yields comparable results, improving over a spectral baseline.","url_abs":"https://arxiv.org/abs/2407.16417v2","url_pdf":"https://arxiv.org/pdf/2407.16417v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"on-the-utility-of-speech-and-audio-foundation","repo_url":"https://github.com/idiap/speech-utility-bioacoustics","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"multi-class-classification","task_name":"Multi-class Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.16417","atlas_url":"https://app.syntology.ai/?focus=2407.16417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16417"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/idiap/speech-utility-bioacoustics","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"8dcb423585156d31","entry":"collate","repo":"idiap/speech-utility-bioacoustics","repo_kind":"official","path":"src/extract_byol.py","file_url":"https://github.com/idiap/speech-utility-bioacoustics/blob/HEAD/src/extract_byol.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"8dcb423585156d31"}},{"code_sha256_prefix":"213879b8eb3bebd4","entry":"unpad","repo":"idiap/speech-utility-bioacoustics","repo_kind":"official","path":"src/extract_byol.py","file_url":"https://github.com/idiap/speech-utility-bioacoustics/blob/HEAD/src/extract_byol.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"213879b8eb3bebd4"}},{"code_sha256_prefix":"62552bdaa51f0964","entry":"collate_fn","repo":"idiap/speech-utility-bioacoustics","repo_kind":"official","path":"src/utils/loader.py","file_url":"https://github.com/idiap/speech-utility-bioacoustics/blob/HEAD/src/utils/loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"62552bdaa51f0964"}},{"code_sha256_prefix":"05f2bdc0c7b2e628","entry":"manual_reflect_pad","repo":"idiap/speech-utility-bioacoustics","repo_kind":"official","path":"src/utils/loader.py","file_url":"https://github.com/idiap/speech-utility-bioacoustics/blob/HEAD/src/utils/loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"05f2bdc0c7b2e628"}},{"code_sha256_prefix":"8ae639e28a78279a","entry":"pad_sequence","repo":"idiap/speech-utility-bioacoustics","repo_kind":"official","path":"src/utils/loader.py","file_url":"https://github.com/idiap/speech-utility-bioacoustics/blob/HEAD/src/utils/loader.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"8ae639e28a78279a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}