{"paper":{"title":"Singing Voice Graph Modeling for SingFake Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.SP"],"primary_cat":"eess.AS","authors_text":"Haibin Wu, Hung-yi Lee, Jyh-Shing Roger Jang, Xuanjun Chen","submitted_at":"2024-06-05T10:02:56Z","abstract_excerpt":"Detecting singing voice deepfakes, or SingFake, involves determining the authenticity and copyright of a singing voice. Existing models for speech deepfake detection have struggled to adapt to unseen attacks in this unique singing voice domain of human vocalization. To bridge the gap, we present a groundbreaking SingGraph model. The model synergizes the capabilities of the MERT acoustic music understanding model for pitch and rhythm analysis with the wav2vec2.0 model for linguistic analysis of lyrics. Additionally, we advocate for using RawBoost and beat matching techniques grounded in music d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03111","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.03111/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}