{"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/learnable-spectro-temporal-receptive-fields","title":"Learnable Spectro-temporal Receptive Fields for Robust Voice Type Discrimination","arxiv_id":"2010.09151","date":"2020-10-19","proceeding":null,"authors":["Tyler Vuong","Yangyang Xia","Richard Stern"],"abstract":"Voice Type Discrimination (VTD) refers to discrimination between regions in a recording where speech was produced by speakers that are physically within proximity of the recording device (\"Live Speech\") from speech and other types of audio that were played back such as traffic noise and television broadcasts (\"Distractor Audio\"). In this work, we propose a deep-learning-based VTD system that features an initial layer of learnable spectro-temporal receptive fields (STRFs). Our approach is also shown to provide very strong performance on a similar spoofing detection task in the ASVspoof 2019 challenge. We evaluate our approach on a new standardized VTD database that was collected to support research in this area. In particular, we study the effect of using learnable STRFs compared to static STRFs or unconstrained kernels. We also show that our system consistently improves a competitive baseline system across a wide range of signal-to-noise ratios on spoofing detection in the presence of VTD distractor noise.","url_abs":"https://arxiv.org/abs/2010.09151v1","url_pdf":"https://arxiv.org/pdf/2010.09151v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"learnable-spectro-temporal-receptive-fields","repo_url":"https://github.com/raymondxyy/strfnet-IS2020","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.09151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.09151"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/raymondxyy/strfnet-IS2020","reach":null}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"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":1,"samples":[{"code_sha256_prefix":"18fbe72ffac82ee3","entry":"conv3x3","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"18fbe72ffac82ee3"}},{"code_sha256_prefix":"c33253e05cf418c6","entry":"is_strf_param","repo":"raymondxyy/strfnet-IS2020","repo_kind":"official","path":"models.py","file_url":"https://github.com/raymondxyy/strfnet-IS2020/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c33253e05cf418c6"}},{"code_sha256_prefix":"1f992aff118e3db9","entry":"nextpow2","repo":"raymondxyy/strfnet-IS2020","repo_kind":"official","path":"utils.py","file_url":"https://github.com/raymondxyy/strfnet-IS2020/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1f992aff118e3db9"}},{"code_sha256_prefix":"08de68b884ebb0e2","entry":"hilbert","repo":"raymondxyy/strfnet-IS2020","repo_kind":"official","path":"utils.py","file_url":"https://github.com/raymondxyy/strfnet-IS2020/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"08de68b884ebb0e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}