{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GFSLX2AYMZSCZXG6MDB3B5RKZZ","short_pith_number":"pith:GFSLX2AY","schema_version":"1.0","canonical_sha256":"3164bbe81866642cdcde60c3b0f62ace628cd848d2c92216dd23091eea9261e5","source":{"kind":"arxiv","id":"2205.01800","version":1},"attestation_state":"computed","paper":{"title":"Synthesized Speech Detection Using Convolutional Transformer-Based Spectrogram Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Edward J. Delp, Emily R. Bartusiak","submitted_at":"2022-05-03T22:05:35Z","abstract_excerpt":"Synthesized speech is common today due to the prevalence of virtual assistants, easy-to-use tools for generating and modifying speech signals, and remote work practices. Synthesized speech can also be used for nefarious purposes, including creating a purported speech signal and attributing it to someone who did not speak the content of the signal. We need methods to detect if a speech signal is synthesized. In this paper, we analyze speech signals in the form of spectrograms with a Compact Convolutional Transformer (CCT) for synthesized speech detection. A CCT utilizes a convolutional layer th"},"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":"2205.01800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-05-03T22:05:35Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"6bddbf7c2bcbc8b7e2c1c07e4e0fb8d1fde8f142f2d29681bce1edea94e445ab","abstract_canon_sha256":"2e86dcce90705d7943a50ec59d68ff533a7ac6df37d96226c1a54e068c70f4d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:22.187850Z","signature_b64":"sjDpkWshEuWEMnZJ6vYB8xFyyc/TSqDH+pHZGS3CzYyYXWp978GrCf4NGOjsWL/Ig1JPLw6SoXPjLP2HxWgICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3164bbe81866642cdcde60c3b0f62ace628cd848d2c92216dd23091eea9261e5","last_reissued_at":"2026-07-05T04:20:22.187374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:22.187374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthesized Speech Detection Using Convolutional Transformer-Based Spectrogram Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Edward J. Delp, Emily R. Bartusiak","submitted_at":"2022-05-03T22:05:35Z","abstract_excerpt":"Synthesized speech is common today due to the prevalence of virtual assistants, easy-to-use tools for generating and modifying speech signals, and remote work practices. Synthesized speech can also be used for nefarious purposes, including creating a purported speech signal and attributing it to someone who did not speak the content of the signal. We need methods to detect if a speech signal is synthesized. In this paper, we analyze speech signals in the form of spectrograms with a Compact Convolutional Transformer (CCT) for synthesized speech detection. A CCT utilizes a convolutional layer th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01800","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/2205.01800/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":"2205.01800","created_at":"2026-07-05T04:20:22.187478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.01800v1","created_at":"2026-07-05T04:20:22.187478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01800","created_at":"2026-07-05T04:20:22.187478+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFSLX2AYMZSC","created_at":"2026-07-05T04:20:22.187478+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFSLX2AYMZSCZXG6","created_at":"2026-07-05T04:20:22.187478+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFSLX2AY","created_at":"2026-07-05T04:20:22.187478+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/GFSLX2AYMZSCZXG6MDB3B5RKZZ","json":"https://pith.science/pith/GFSLX2AYMZSCZXG6MDB3B5RKZZ.json","graph_json":"https://pith.science/api/pith-number/GFSLX2AYMZSCZXG6MDB3B5RKZZ/graph.json","events_json":"https://pith.science/api/pith-number/GFSLX2AYMZSCZXG6MDB3B5RKZZ/events.json","paper":"https://pith.science/paper/GFSLX2AY"},"agent_actions":{"view_html":"https://pith.science/pith/GFSLX2AYMZSCZXG6MDB3B5RKZZ","download_json":"https://pith.science/pith/GFSLX2AYMZSCZXG6MDB3B5RKZZ.json","view_paper":"https://pith.science/paper/GFSLX2AY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.01800&json=true","fetch_graph":"https://pith.science/api/pith-number/GFSLX2AYMZSCZXG6MDB3B5RKZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GFSLX2AYMZSCZXG6MDB3B5RKZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFSLX2AYMZSCZXG6MDB3B5RKZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFSLX2AYMZSCZXG6MDB3B5RKZZ/action/storage_attestation","attest_author":"https://pith.science/pith/GFSLX2AYMZSCZXG6MDB3B5RKZZ/action/author_attestation","sign_citation":"https://pith.science/pith/GFSLX2AYMZSCZXG6MDB3B5RKZZ/action/citation_signature","submit_replication":"https://pith.science/pith/GFSLX2AYMZSCZXG6MDB3B5RKZZ/action/replication_record"}},"created_at":"2026-07-05T04:20:22.187478+00:00","updated_at":"2026-07-05T04:20:22.187478+00:00"}