{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7PKY5GDHK5T5ZHS4YGIPZTQTYC","short_pith_number":"pith:7PKY5GDH","schema_version":"1.0","canonical_sha256":"fbd58e98675767dc9e5cc190fcce13c0acf5ec2b6eb192763a456dd4ae463967","source":{"kind":"arxiv","id":"2412.08247","version":2},"attestation_state":"computed","paper":{"title":"MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Junjie Li, Ke Zhang, Kong Aik Lee, Man-Wai Mak, Shuai Wang","submitted_at":"2024-12-11T09:55:09Z","abstract_excerpt":"Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate the speech of a specific target speaker from an audio mixture using time-synchronized visual cues. In real-world scenarios, visual cues are not always available due to various impairments, which undermines the stability of AV-TSE. Despite this challenge, humans can maintain attentional momentum over time, even when the target speaker is not visible. In this paper, we introduce the Momentum Multi-modal target Speaker Extraction (MoMuSE), which retains a speaker identity momentum in memory, enabling the model to continuously track t"},"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":"2412.08247","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-12-11T09:55:09Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"d3f82789a074e9f0255b240bcc711ad6b6be5a0a010a6e93fe19c505175249d7","abstract_canon_sha256":"75af4279639e34080b15f806013acb8ad1b539b2e819b2b75a06315c3cb23e38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:51.158688Z","signature_b64":"7GawyHI8iM9Dnvu+JzdrQq0bzu7QRncHXVDAZ+xiJD0VztFWVIqWmhDuQ7mlm45KGIYIcSIEW60X2m0KsBtTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbd58e98675767dc9e5cc190fcce13c0acf5ec2b6eb192763a456dd4ae463967","last_reissued_at":"2026-07-05T10:41:51.158191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:51.158191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haizhou Li, Junjie Li, Ke Zhang, Kong Aik Lee, Man-Wai Mak, Shuai Wang","submitted_at":"2024-12-11T09:55:09Z","abstract_excerpt":"Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate the speech of a specific target speaker from an audio mixture using time-synchronized visual cues. In real-world scenarios, visual cues are not always available due to various impairments, which undermines the stability of AV-TSE. Despite this challenge, humans can maintain attentional momentum over time, even when the target speaker is not visible. In this paper, we introduce the Momentum Multi-modal target Speaker Extraction (MoMuSE), which retains a speaker identity momentum in memory, enabling the model to continuously track t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08247","kind":"arxiv","version":2},"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/2412.08247/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":"2412.08247","created_at":"2026-07-05T10:41:51.158249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08247v2","created_at":"2026-07-05T10:41:51.158249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08247","created_at":"2026-07-05T10:41:51.158249+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PKY5GDHK5T5","created_at":"2026-07-05T10:41:51.158249+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PKY5GDHK5T5ZHS4","created_at":"2026-07-05T10:41:51.158249+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PKY5GDH","created_at":"2026-07-05T10:41:51.158249+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/7PKY5GDHK5T5ZHS4YGIPZTQTYC","json":"https://pith.science/pith/7PKY5GDHK5T5ZHS4YGIPZTQTYC.json","graph_json":"https://pith.science/api/pith-number/7PKY5GDHK5T5ZHS4YGIPZTQTYC/graph.json","events_json":"https://pith.science/api/pith-number/7PKY5GDHK5T5ZHS4YGIPZTQTYC/events.json","paper":"https://pith.science/paper/7PKY5GDH"},"agent_actions":{"view_html":"https://pith.science/pith/7PKY5GDHK5T5ZHS4YGIPZTQTYC","download_json":"https://pith.science/pith/7PKY5GDHK5T5ZHS4YGIPZTQTYC.json","view_paper":"https://pith.science/paper/7PKY5GDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08247&json=true","fetch_graph":"https://pith.science/api/pith-number/7PKY5GDHK5T5ZHS4YGIPZTQTYC/graph.json","fetch_events":"https://pith.science/api/pith-number/7PKY5GDHK5T5ZHS4YGIPZTQTYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PKY5GDHK5T5ZHS4YGIPZTQTYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PKY5GDHK5T5ZHS4YGIPZTQTYC/action/storage_attestation","attest_author":"https://pith.science/pith/7PKY5GDHK5T5ZHS4YGIPZTQTYC/action/author_attestation","sign_citation":"https://pith.science/pith/7PKY5GDHK5T5ZHS4YGIPZTQTYC/action/citation_signature","submit_replication":"https://pith.science/pith/7PKY5GDHK5T5ZHS4YGIPZTQTYC/action/replication_record"}},"created_at":"2026-07-05T10:41:51.158249+00:00","updated_at":"2026-07-05T10:41:51.158249+00:00"}