{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PLUW6BU65WOCFI534VG5ZKI6PD","short_pith_number":"pith:PLUW6BU6","schema_version":"1.0","canonical_sha256":"7ae96f069eed9c22a3bbe54ddca91e78c097d5be7fb675102af8d2bf029f3b00","source":{"kind":"arxiv","id":"2401.14185","version":1},"attestation_state":"computed","paper":{"title":"TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Li, Samuel Pegg, Xiaolin Hu","submitted_at":"2024-01-25T13:47:22Z","abstract_excerpt":"Audio-visual speech separation has gained significant traction in recent years due to its potential applications in various fields such as speech recognition, diarization, scene analysis and assistive technologies. Designing a lightweight audio-visual speech separation network is important for low-latency applications, but existing methods often require higher computational costs and more parameters to achieve better separation performance. In this paper, we present an audio-visual speech separation model called Top-Down-Fusion Net (TDFNet), a state-of-the-art (SOTA) model for audio-visual spe"},"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":"2401.14185","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-01-25T13:47:22Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"f0a7dd438457df16837fffde8905a6903f5a07175d0d387a39ded2ecfe844bf1","abstract_canon_sha256":"d82f66c90ac37819b4f01ce0f5542930d71cdba853bcc1ee701ea699f434245b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:32.559382Z","signature_b64":"kDZNKce8ZbKwnCiEsEHump4cBWr8yP4Dx7k6zsN0oWgupIN5zd2CENv1xXScpdtdmYutf0fF4jr9ZDkWXyoODg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ae96f069eed9c22a3bbe54ddca91e78c097d5be7fb675102af8d2bf029f3b00","last_reissued_at":"2026-07-05T07:37:32.558965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:32.558965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Li, Samuel Pegg, Xiaolin Hu","submitted_at":"2024-01-25T13:47:22Z","abstract_excerpt":"Audio-visual speech separation has gained significant traction in recent years due to its potential applications in various fields such as speech recognition, diarization, scene analysis and assistive technologies. Designing a lightweight audio-visual speech separation network is important for low-latency applications, but existing methods often require higher computational costs and more parameters to achieve better separation performance. In this paper, we present an audio-visual speech separation model called Top-Down-Fusion Net (TDFNet), a state-of-the-art (SOTA) model for audio-visual spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14185","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/2401.14185/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":"2401.14185","created_at":"2026-07-05T07:37:32.559013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14185v1","created_at":"2026-07-05T07:37:32.559013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14185","created_at":"2026-07-05T07:37:32.559013+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLUW6BU65WOC","created_at":"2026-07-05T07:37:32.559013+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLUW6BU65WOCFI53","created_at":"2026-07-05T07:37:32.559013+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLUW6BU6","created_at":"2026-07-05T07:37:32.559013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18695","citing_title":"AI for Regulatory Affairs: Balancing Accuracy, Interpretability, and Computational Cost in Medical Device Classification","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD","json":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD.json","graph_json":"https://pith.science/api/pith-number/PLUW6BU65WOCFI534VG5ZKI6PD/graph.json","events_json":"https://pith.science/api/pith-number/PLUW6BU65WOCFI534VG5ZKI6PD/events.json","paper":"https://pith.science/paper/PLUW6BU6"},"agent_actions":{"view_html":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD","download_json":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD.json","view_paper":"https://pith.science/paper/PLUW6BU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14185&json=true","fetch_graph":"https://pith.science/api/pith-number/PLUW6BU65WOCFI534VG5ZKI6PD/graph.json","fetch_events":"https://pith.science/api/pith-number/PLUW6BU65WOCFI534VG5ZKI6PD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD/action/storage_attestation","attest_author":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD/action/author_attestation","sign_citation":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD/action/citation_signature","submit_replication":"https://pith.science/pith/PLUW6BU65WOCFI534VG5ZKI6PD/action/replication_record"}},"created_at":"2026-07-05T07:37:32.559013+00:00","updated_at":"2026-07-05T07:37:32.559013+00:00"}