{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OCANAPESUQVE3VE6URIJ6TNS3X","short_pith_number":"pith:OCANAPES","schema_version":"1.0","canonical_sha256":"7080d03c92a42a4dd49ea4509f4db2ddc42c509b7041d18a7c2e8ffad98bfbbe","source":{"kind":"arxiv","id":"2403.16078","version":1},"attestation_state":"computed","paper":{"title":"Target Speech Extraction with Pre-trained AV-HuBERT and Mask-And-Recover Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Helen Meng, Wenxuan Wu, Xixin Wu, Xueyuan Chen","submitted_at":"2024-03-24T09:42:05Z","abstract_excerpt":"Audio-visual target speech extraction (AV-TSE) is one of the enabling technologies in robotics and many audio-visual applications. One of the challenges of AV-TSE is how to effectively utilize audio-visual synchronization information in the process. AV-HuBERT can be a useful pre-trained model for lip-reading, which has not been adopted by AV-TSE. In this paper, we would like to explore the way to integrate a pre-trained AV-HuBERT into our AV-TSE system. We have good reasons to expect an improved performance. To benefit from the inter and intra-modality correlations, we also propose a novel Mas"},"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":"2403.16078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-24T09:42:05Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"24fb6a94fe5aaead6a7e4fbb8ecbe169d598e76fdb286768d6cd512c4f0c71de","abstract_canon_sha256":"5bfa0840b41bcb6e4b858e4e375007d1c6d513c7985738c4ed83d2b28cf1c71f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:10.264804Z","signature_b64":"9FQS1bsl5glOSC1i2kyXl9j9G8F29gwHMvYTeC6Ro+ZQD6QhHBKX1o6gO4VC87Wh6xFi/gbes/r5+BrGEfeMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7080d03c92a42a4dd49ea4509f4db2ddc42c509b7041d18a7c2e8ffad98bfbbe","last_reissued_at":"2026-07-05T08:00:10.264358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:10.264358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Target Speech Extraction with Pre-trained AV-HuBERT and Mask-And-Recover Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Helen Meng, Wenxuan Wu, Xixin Wu, Xueyuan Chen","submitted_at":"2024-03-24T09:42:05Z","abstract_excerpt":"Audio-visual target speech extraction (AV-TSE) is one of the enabling technologies in robotics and many audio-visual applications. One of the challenges of AV-TSE is how to effectively utilize audio-visual synchronization information in the process. AV-HuBERT can be a useful pre-trained model for lip-reading, which has not been adopted by AV-TSE. In this paper, we would like to explore the way to integrate a pre-trained AV-HuBERT into our AV-TSE system. We have good reasons to expect an improved performance. To benefit from the inter and intra-modality correlations, we also propose a novel Mas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16078","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/2403.16078/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":"2403.16078","created_at":"2026-07-05T08:00:10.264416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16078v1","created_at":"2026-07-05T08:00:10.264416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16078","created_at":"2026-07-05T08:00:10.264416+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCANAPESUQVE","created_at":"2026-07-05T08:00:10.264416+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCANAPESUQVE3VE6","created_at":"2026-07-05T08:00:10.264416+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCANAPES","created_at":"2026-07-05T08:00:10.264416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.00350","citing_title":"DiffDSR: Dysarthric Speech Reconstruction Using Latent Diffusion Model","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCANAPESUQVE3VE6URIJ6TNS3X","json":"https://pith.science/pith/OCANAPESUQVE3VE6URIJ6TNS3X.json","graph_json":"https://pith.science/api/pith-number/OCANAPESUQVE3VE6URIJ6TNS3X/graph.json","events_json":"https://pith.science/api/pith-number/OCANAPESUQVE3VE6URIJ6TNS3X/events.json","paper":"https://pith.science/paper/OCANAPES"},"agent_actions":{"view_html":"https://pith.science/pith/OCANAPESUQVE3VE6URIJ6TNS3X","download_json":"https://pith.science/pith/OCANAPESUQVE3VE6URIJ6TNS3X.json","view_paper":"https://pith.science/paper/OCANAPES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16078&json=true","fetch_graph":"https://pith.science/api/pith-number/OCANAPESUQVE3VE6URIJ6TNS3X/graph.json","fetch_events":"https://pith.science/api/pith-number/OCANAPESUQVE3VE6URIJ6TNS3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCANAPESUQVE3VE6URIJ6TNS3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCANAPESUQVE3VE6URIJ6TNS3X/action/storage_attestation","attest_author":"https://pith.science/pith/OCANAPESUQVE3VE6URIJ6TNS3X/action/author_attestation","sign_citation":"https://pith.science/pith/OCANAPESUQVE3VE6URIJ6TNS3X/action/citation_signature","submit_replication":"https://pith.science/pith/OCANAPESUQVE3VE6URIJ6TNS3X/action/replication_record"}},"created_at":"2026-07-05T08:00:10.264416+00:00","updated_at":"2026-07-05T08:00:10.264416+00:00"}