{"url":"/task/synthetic-speech-detection","name":"Synthetic Speech Detection","slug":"synthetic-speech-detection","description_markdown":"Detect fake synthetic speech generated using machine learning","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":29,"papers_with_code":12,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/sonics","name":"SONICS","full_name":"Synthetic Or Not - Identifying Counterfeit Songs","num_papers_in_archive":3},{"url":"/dataset/deep-voice-deepfake-voice-recognition","name":"DEEP-VOICE: DeepFake Voice Recognition","full_name":"Jordan Bird","num_papers_in_archive":1},{"url":"/dataset/shiftyspeech","name":"ShiftySpeech","full_name":"","num_papers_in_archive":1},{"url":"/dataset/synthetic-speech-attribution","name":"Synthetic Speech Attribution","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/deepfake-detection","name":"DeepFake Detection"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":12,"of":12,"tagged_in_all":29,"items":[{"url":"/paper/sonics-synthetic-or-not-identifying","title":"SONICS: Synthetic Or Not -- Identifying Counterfeit Songs","date":"2024-08-26","arxiv_id":"2408.14080","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":9}},{"url":"/paper/convnext-based-neural-network-for-anti","title":"ConvNeXt Based Neural Network for Audio Anti-Spoofing","date":"2022-09-14","arxiv_id":"2209.06434","repositories_listed":2,"syntology":null},{"url":"/paper/ur-channel-robust-synthetic-speech-detection","title":"UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021","date":"2021-07-26","arxiv_id":"2107.12018","repositories_listed":2,"syntology":null},{"url":"/paper/towards-end-to-end-synthetic-speech-detection","title":"Towards End-to-End Synthetic Speech Detection","date":"2021-06-11","arxiv_id":"2106.06341","repositories_listed":2,"syntology":null},{"url":"/paper/replay-and-synthetic-speech-detection-with","title":"Replay and Synthetic Speech Detection with Res2net Architecture","date":"2020-10-28","arxiv_id":"2010.15006","repositories_listed":2,"syntology":null},{"url":"/paper/pushing-the-performance-of-synthetic-speech","title":"Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models","date":"2025-06-17","arxiv_id":"2506.14153","repositories_listed":1,"syntology":null},{"url":"/paper/less-is-more-for-synthetic-speech-detection","title":"ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts","date":"2025-02-08","arxiv_id":"2502.05674","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-channel-modeling-in-multi-head-self","title":"Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection","date":"2024-06-25","arxiv_id":"2406.17376","repositories_listed":1,"syntology":null},{"url":"/paper/singfake-singing-voice-deepfake-detection","title":"SingFake: Singing Voice Deepfake Detection","date":"2023-09-14","arxiv_id":"2309.07525","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/the-sound-of-silence-efficiency-of-first","title":"The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection","date":"2022-10-06","arxiv_id":"2210.02746","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-learning-improves-synthetic-speech","title":"Multi-task learning improves synthetic speech detection","date":"2022-04-27","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fmfcc-a-a-challenging-mandarin-dataset-for","title":"FMFCC-A: A Challenging Mandarin Dataset for Synthetic Speech Detection","date":"2021-10-18","arxiv_id":"2110.09441","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}