{"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/stc-antispoofing-systems-for-the-asvspoof2019","title":"STC Antispoofing Systems for the ASVspoof2019 Challenge","arxiv_id":"1904.05576","date":"2019-04-11","proceeding":null,"authors":["Galina Lavrentyeva","Sergey Novoselov","Andzhukaev Tseren","Marina Volkova","Artem Gorlanov","Alexandr Kozlov"],"abstract":"This paper describes the Speech Technology Center (STC) antispoofing systems\nsubmitted to the ASVspoof 2019 challenge. The ASVspoof2019 is the extended\nversion of the previous challenges and includes 2 evaluation conditions:\nlogical access use-case scenario with speech synthesis and voice conversion\nattack types and physical access use-case scenario with replay attacks. During\nthe challenge we developed anti-spoofing solutions for both scenarios. The\nproposed systems are implemented using deep learning approach and are based on\ndifferent types of acoustic features. We enhanced Light CNN architecture\npreviously considered by the authors for replay attacks detection and which\nperformed high spoofing detection quality during the ASVspoof2017 challenge. In\nparticular here we investigate the efficiency of angular margin based softmax\nactivation for training robust deep Light CNN classifier to solve the\nmentioned-above tasks. Submitted systems achieved EER of 1.86% in logical\naccess scenario and 0.54% in physical access scenario on the evaluation part of\nthe Challenge corpora. High performance obtained for the unknown types of\nspoofing attacks demonstrates the stability of the offered approach in both\nevaluation conditions.","url_abs":"http://arxiv.org/abs/1904.05576v1","url_pdf":"http://arxiv.org/pdf/1904.05576v1.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":"stc-antispoofing-systems-for-the-asvspoof2019","repo_url":"https://github.com/ozora-ogino/LCNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.05576","atlas_url":"https://app.syntology.ai/?focus=1904.05576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05576"}},"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/ozora-ogino/LCNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"62537d31a61d8fe6","entry":"calculate_eer","repo":"ozora-ogino/LCNN","repo_kind":"listed","path":"src/metrics.py","file_url":"https://github.com/ozora-ogino/LCNN/blob/HEAD/src/metrics.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"62537d31a61d8fe6"}},{"code_sha256_prefix":"94dc2b3628fe1630","entry":"MaxOutDense","repo":"ozora-ogino/LCNN","repo_kind":"listed","path":"src/model/lcnn.py","file_url":"https://github.com/ozora-ogino/LCNN/blob/HEAD/src/model/lcnn.py","link_basis":"harvester_set","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":"94dc2b3628fe1630"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}