{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M44TX2KBXWDLWN7D5N7UTMLQ7Z","short_pith_number":"pith:M44TX2KB","schema_version":"1.0","canonical_sha256":"67393be941bd86bb37e3eb7f49b170fe61c652ef317166634f5728a7238743f0","source":{"kind":"arxiv","id":"2210.17222","version":1},"attestation_state":"computed","paper":{"title":"Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Clara Borrelli, Davide Salvi, Luigi Attorresi, Paolo Bestagini, Stefano Tubaro","submitted_at":"2022-10-31T11:03:03Z","abstract_excerpt":"The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work we present a novel approach for synthetic speech detection, exploiting the combination of two high-level semantic properties of the human voice. On one side, we focus on speaker identity cues and represent them as speaker embeddings extracted using a state-of-the-art method for the automatic speaker verification task. On the other side, voice prosody, intende"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.17222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-31T11:03:03Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"8cf1b7685eee2f142c5be940872da0ae22365fd4915275be7d0630aecf90e3a4","abstract_canon_sha256":"e13d0d6eb8d4e557b7937f6808036d7d3cf83a21a506fe950149c640d8f46e12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:56.021740Z","signature_b64":"ozmLPKpvtNAqe4jXv34j+iBmanGg8cdwy9s212s4YVDPqJYfIl8ufcZM1f00AH/VJcfcFbmFSvTwKC/DQ84SCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67393be941bd86bb37e3eb7f49b170fe61c652ef317166634f5728a7238743f0","last_reissued_at":"2026-07-05T05:11:56.021229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:56.021229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Clara Borrelli, Davide Salvi, Luigi Attorresi, Paolo Bestagini, Stefano Tubaro","submitted_at":"2022-10-31T11:03:03Z","abstract_excerpt":"The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work we present a novel approach for synthetic speech detection, exploiting the combination of two high-level semantic properties of the human voice. On one side, we focus on speaker identity cues and represent them as speaker embeddings extracted using a state-of-the-art method for the automatic speaker verification task. On the other side, voice prosody, intende"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17222","kind":"arxiv","version":1},"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/2210.17222/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.17222","created_at":"2026-07-05T05:11:56.021334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.17222v1","created_at":"2026-07-05T05:11:56.021334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17222","created_at":"2026-07-05T05:11:56.021334+00:00"},{"alias_kind":"pith_short_12","alias_value":"M44TX2KBXWDL","created_at":"2026-07-05T05:11:56.021334+00:00"},{"alias_kind":"pith_short_16","alias_value":"M44TX2KBXWDLWN7D","created_at":"2026-07-05T05:11:56.021334+00:00"},{"alias_kind":"pith_short_8","alias_value":"M44TX2KB","created_at":"2026-07-05T05:11:56.021334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17513","citing_title":"What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M44TX2KBXWDLWN7D5N7UTMLQ7Z","json":"https://pith.science/pith/M44TX2KBXWDLWN7D5N7UTMLQ7Z.json","graph_json":"https://pith.science/api/pith-number/M44TX2KBXWDLWN7D5N7UTMLQ7Z/graph.json","events_json":"https://pith.science/api/pith-number/M44TX2KBXWDLWN7D5N7UTMLQ7Z/events.json","paper":"https://pith.science/paper/M44TX2KB"},"agent_actions":{"view_html":"https://pith.science/pith/M44TX2KBXWDLWN7D5N7UTMLQ7Z","download_json":"https://pith.science/pith/M44TX2KBXWDLWN7D5N7UTMLQ7Z.json","view_paper":"https://pith.science/paper/M44TX2KB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.17222&json=true","fetch_graph":"https://pith.science/api/pith-number/M44TX2KBXWDLWN7D5N7UTMLQ7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/M44TX2KBXWDLWN7D5N7UTMLQ7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M44TX2KBXWDLWN7D5N7UTMLQ7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M44TX2KBXWDLWN7D5N7UTMLQ7Z/action/storage_attestation","attest_author":"https://pith.science/pith/M44TX2KBXWDLWN7D5N7UTMLQ7Z/action/author_attestation","sign_citation":"https://pith.science/pith/M44TX2KBXWDLWN7D5N7UTMLQ7Z/action/citation_signature","submit_replication":"https://pith.science/pith/M44TX2KBXWDLWN7D5N7UTMLQ7Z/action/replication_record"}},"created_at":"2026-07-05T05:11:56.021334+00:00","updated_at":"2026-07-05T05:11:56.021334+00:00"}