{"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/assert-anti-spoofing-with-squeeze-excitation","title":"ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks","arxiv_id":"1904.01120","date":"2019-04-01","proceeding":null,"authors":["Cheng-I Lai","Nanxin Chen","Jesús Villalba","Najim Dehak"],"abstract":"We present JHU's system submission to the ASVspoof 2019 Challenge:\nAnti-Spoofing with Squeeze-Excitation and Residual neTworks (ASSERT).\nAnti-spoofing has gathered more and more attention since the inauguration of\nthe ASVspoof Challenges, and ASVspoof 2019 dedicates to address attacks from\nall three major types: text-to-speech, voice conversion, and replay. Built upon\nprevious research work on Deep Neural Network (DNN), ASSERT is a pipeline for\nDNN-based approach to anti-spoofing. ASSERT has four components: feature\nengineering, DNN models, network optimization and system combination, where the\nDNN models are variants of squeeze-excitation and residual networks. We\nconducted an ablation study of the effectiveness of each component on the\nASVspoof 2019 corpus, and experimental results showed that ASSERT obtained more\nthan 93% and 17% relative improvements over the baseline systems in the two\nsub-challenges in ASVspooof 2019, ranking ASSERT one of the top performing\nsystems. Code and pretrained models will be made publicly available.","url_abs":"http://arxiv.org/abs/1904.01120v1","url_pdf":"http://arxiv.org/pdf/1904.01120v1.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":"assert-anti-spoofing-with-squeeze-excitation","repo_url":"https://github.com/jefflai108/ASSERT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1904.01120","atlas_url":"https://app.syntology.ai/?focus=1904.01120","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}