{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q4YW35W7KPI2FMJL6OJOZSDRFM","short_pith_number":"pith:Q4YW35W7","schema_version":"1.0","canonical_sha256":"87316df6df53d1a2b12bf392ecc8712b2185aa9f1363b68ac5cafc59fd089c74","source":{"kind":"arxiv","id":"2505.15136","version":1},"attestation_state":"computed","paper":{"title":"Hybrid Audio Detection Using Fine-Tuned Audio Spectrogram Transformers: A Dataset-Driven Evaluation of Mixed AI-Human Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Hu, Kunyang Huang","submitted_at":"2025-05-21T05:43:41Z","abstract_excerpt":"The rapid advancement of artificial intelligence (AI) has enabled sophisticated audio generation and voice cloning technologies, posing significant security risks for applications reliant on voice authentication. While existing datasets and models primarily focus on distinguishing between human and fully synthetic speech, real-world attacks often involve audio that combines both genuine and cloned segments. To address this gap, we construct a novel hybrid audio dataset incorporating human, AI-generated, cloned, and mixed audio samples. We further propose fine-tuned Audio Spectrogram Transforme"},"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":"2505.15136","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-21T05:43:41Z","cross_cats_sorted":["cs.CR","eess.AS"],"title_canon_sha256":"f9f766d7192e278452c5bd8ef566085f08c9ca1a3976a8044524fad72cf18a79","abstract_canon_sha256":"c32bb9ca3da273fa9feedfc09fc1b87b6d1eeb8c412fa7add8c696699a98680c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:41.150154Z","signature_b64":"gjU6H6iKQYnHWSbdEXQhD2T48S2JkBQ+CjHwnqCtnXbg1ha8Awiq4fTPKWR4BeHVS3ih1W1Y9aKxUo9Q7sXXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87316df6df53d1a2b12bf392ecc8712b2185aa9f1363b68ac5cafc59fd089c74","last_reissued_at":"2026-07-05T11:06:41.149690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:41.149690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Audio Detection Using Fine-Tuned Audio Spectrogram Transformers: A Dataset-Driven Evaluation of Mixed AI-Human Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Hu, Kunyang Huang","submitted_at":"2025-05-21T05:43:41Z","abstract_excerpt":"The rapid advancement of artificial intelligence (AI) has enabled sophisticated audio generation and voice cloning technologies, posing significant security risks for applications reliant on voice authentication. While existing datasets and models primarily focus on distinguishing between human and fully synthetic speech, real-world attacks often involve audio that combines both genuine and cloned segments. To address this gap, we construct a novel hybrid audio dataset incorporating human, AI-generated, cloned, and mixed audio samples. We further propose fine-tuned Audio Spectrogram Transforme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15136","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/2505.15136/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":"2505.15136","created_at":"2026-07-05T11:06:41.149746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15136v1","created_at":"2026-07-05T11:06:41.149746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15136","created_at":"2026-07-05T11:06:41.149746+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4YW35W7KPI2","created_at":"2026-07-05T11:06:41.149746+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4YW35W7KPI2FMJL","created_at":"2026-07-05T11:06:41.149746+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4YW35W7","created_at":"2026-07-05T11:06:41.149746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4YW35W7KPI2FMJL6OJOZSDRFM","json":"https://pith.science/pith/Q4YW35W7KPI2FMJL6OJOZSDRFM.json","graph_json":"https://pith.science/api/pith-number/Q4YW35W7KPI2FMJL6OJOZSDRFM/graph.json","events_json":"https://pith.science/api/pith-number/Q4YW35W7KPI2FMJL6OJOZSDRFM/events.json","paper":"https://pith.science/paper/Q4YW35W7"},"agent_actions":{"view_html":"https://pith.science/pith/Q4YW35W7KPI2FMJL6OJOZSDRFM","download_json":"https://pith.science/pith/Q4YW35W7KPI2FMJL6OJOZSDRFM.json","view_paper":"https://pith.science/paper/Q4YW35W7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15136&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4YW35W7KPI2FMJL6OJOZSDRFM/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4YW35W7KPI2FMJL6OJOZSDRFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4YW35W7KPI2FMJL6OJOZSDRFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4YW35W7KPI2FMJL6OJOZSDRFM/action/storage_attestation","attest_author":"https://pith.science/pith/Q4YW35W7KPI2FMJL6OJOZSDRFM/action/author_attestation","sign_citation":"https://pith.science/pith/Q4YW35W7KPI2FMJL6OJOZSDRFM/action/citation_signature","submit_replication":"https://pith.science/pith/Q4YW35W7KPI2FMJL6OJOZSDRFM/action/replication_record"}},"created_at":"2026-07-05T11:06:41.149746+00:00","updated_at":"2026-07-05T11:06:41.149746+00:00"}