{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VIN6YB6OLMMBJQT7FFBQMA4EFX","short_pith_number":"pith:VIN6YB6O","schema_version":"1.0","canonical_sha256":"aa1bec07ce5b1814c27f29430603842df435972893dfc638afe7df6a79f41177","source":{"kind":"arxiv","id":"2305.12831","version":3},"attestation_state":"computed","paper":{"title":"Target Active Speaker Detection with Audio-visual Cues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Ruijie Tao, Yidi Jiang, Zexu Pan","submitted_at":"2023-05-22T08:52:42Z","abstract_excerpt":"In active speaker detection (ASD), we would like to detect whether an on-screen person is speaking based on audio-visual cues. Previous studies have primarily focused on modeling audio-visual synchronization cue, which depends on the video quality of the lip region of a speaker. In real-world applications, it is possible that we can also have the reference speech of the on-screen speaker. To benefit from both facial cue and reference speech, we propose the Target Speaker TalkNet (TS-TalkNet), which leverages a pre-enrolled speaker embedding to complement the audio-visual synchronization cue in"},"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":"2305.12831","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-22T08:52:42Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"305a6d391360105571c84c5ed8d41a8d866232aa21cc2089789b78c7da5f4312","abstract_canon_sha256":"75efd17787b5df563949f0280d4ca6512fab7761a09273a7012e49785840d06c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:41.193408Z","signature_b64":"uX+GN3GVUQhm7tvsi+eoHEOw9a4DCOWzpklENKKYN3Lx985rbmHcA3Evh6Oe+tvGWRr+aFLoMqm4UFgusrCJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa1bec07ce5b1814c27f29430603842df435972893dfc638afe7df6a79f41177","last_reissued_at":"2026-07-05T06:19:41.192925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:41.192925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Target Active Speaker Detection with Audio-visual Cues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Haizhou Li, Ruijie Tao, Yidi Jiang, Zexu Pan","submitted_at":"2023-05-22T08:52:42Z","abstract_excerpt":"In active speaker detection (ASD), we would like to detect whether an on-screen person is speaking based on audio-visual cues. Previous studies have primarily focused on modeling audio-visual synchronization cue, which depends on the video quality of the lip region of a speaker. In real-world applications, it is possible that we can also have the reference speech of the on-screen speaker. To benefit from both facial cue and reference speech, we propose the Target Speaker TalkNet (TS-TalkNet), which leverages a pre-enrolled speaker embedding to complement the audio-visual synchronization cue in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12831","kind":"arxiv","version":3},"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/2305.12831/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":"2305.12831","created_at":"2026-07-05T06:19:41.192981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12831v3","created_at":"2026-07-05T06:19:41.192981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12831","created_at":"2026-07-05T06:19:41.192981+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIN6YB6OLMMB","created_at":"2026-07-05T06:19:41.192981+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIN6YB6OLMMBJQT7","created_at":"2026-07-05T06:19:41.192981+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIN6YB6O","created_at":"2026-07-05T06:19:41.192981+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/VIN6YB6OLMMBJQT7FFBQMA4EFX","json":"https://pith.science/pith/VIN6YB6OLMMBJQT7FFBQMA4EFX.json","graph_json":"https://pith.science/api/pith-number/VIN6YB6OLMMBJQT7FFBQMA4EFX/graph.json","events_json":"https://pith.science/api/pith-number/VIN6YB6OLMMBJQT7FFBQMA4EFX/events.json","paper":"https://pith.science/paper/VIN6YB6O"},"agent_actions":{"view_html":"https://pith.science/pith/VIN6YB6OLMMBJQT7FFBQMA4EFX","download_json":"https://pith.science/pith/VIN6YB6OLMMBJQT7FFBQMA4EFX.json","view_paper":"https://pith.science/paper/VIN6YB6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12831&json=true","fetch_graph":"https://pith.science/api/pith-number/VIN6YB6OLMMBJQT7FFBQMA4EFX/graph.json","fetch_events":"https://pith.science/api/pith-number/VIN6YB6OLMMBJQT7FFBQMA4EFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIN6YB6OLMMBJQT7FFBQMA4EFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIN6YB6OLMMBJQT7FFBQMA4EFX/action/storage_attestation","attest_author":"https://pith.science/pith/VIN6YB6OLMMBJQT7FFBQMA4EFX/action/author_attestation","sign_citation":"https://pith.science/pith/VIN6YB6OLMMBJQT7FFBQMA4EFX/action/citation_signature","submit_replication":"https://pith.science/pith/VIN6YB6OLMMBJQT7FFBQMA4EFX/action/replication_record"}},"created_at":"2026-07-05T06:19:41.192981+00:00","updated_at":"2026-07-05T06:19:41.192981+00:00"}