{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SMS45R55I7EMCH6TNAWHHYYZIK","short_pith_number":"pith:SMS45R55","schema_version":"1.0","canonical_sha256":"9325cec7bd47c8c11fd3682c73e31942b6a6d7ed470106462d24b30b83e876b9","source":{"kind":"arxiv","id":"2205.07180","version":2},"attestation_state":"computed","paper":{"title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdelrahman Mohamed, Bowen Shi, Wei-Ning Hsu","submitted_at":"2022-05-15T04:48:41Z","abstract_excerpt":"This paper investigates self-supervised pre-training for audio-visual speaker representation learning where a visual stream showing the speaker's mouth area is used alongside speech as inputs. Our study focuses on the Audio-Visual Hidden Unit BERT (AV-HuBERT) approach, a recently developed general-purpose audio-visual speech pre-training framework. We conducted extensive experiments probing the effectiveness of pre-training and visual modality. Experimental results suggest that AV-HuBERT generalizes decently to speaker related downstream tasks, improving label efficiency by roughly ten fold fo"},"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":"2205.07180","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-15T04:48:41Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"78d99ce68562ce0b9f19ac6ea169c5cb9d801bdf596ee552b809781b2c593269","abstract_canon_sha256":"89b1d0900b64ac6280fe0ef7fa5e0e7df7dbf8eaedf6dc2b7bbdad193233935c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:27.304364Z","signature_b64":"aNjEH1duuduRspgbW2qbo8UfjqeuG05aYP66b4zWN7s6eeFcRSlMcqwwxL7OVk9CezcyabdikGVQ7VsbbS8eBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9325cec7bd47c8c11fd3682c73e31942b6a6d7ed470106462d24b30b83e876b9","last_reissued_at":"2026-07-05T04:40:27.303865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:27.303865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdelrahman Mohamed, Bowen Shi, Wei-Ning Hsu","submitted_at":"2022-05-15T04:48:41Z","abstract_excerpt":"This paper investigates self-supervised pre-training for audio-visual speaker representation learning where a visual stream showing the speaker's mouth area is used alongside speech as inputs. Our study focuses on the Audio-Visual Hidden Unit BERT (AV-HuBERT) approach, a recently developed general-purpose audio-visual speech pre-training framework. We conducted extensive experiments probing the effectiveness of pre-training and visual modality. Experimental results suggest that AV-HuBERT generalizes decently to speaker related downstream tasks, improving label efficiency by roughly ten fold fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07180","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/2205.07180/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":"2205.07180","created_at":"2026-07-05T04:40:27.303929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.07180v2","created_at":"2026-07-05T04:40:27.303929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07180","created_at":"2026-07-05T04:40:27.303929+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMS45R55I7EM","created_at":"2026-07-05T04:40:27.303929+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMS45R55I7EMCH6T","created_at":"2026-07-05T04:40:27.303929+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMS45R55","created_at":"2026-07-05T04:40:27.303929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.17690","citing_title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMS45R55I7EMCH6TNAWHHYYZIK","json":"https://pith.science/pith/SMS45R55I7EMCH6TNAWHHYYZIK.json","graph_json":"https://pith.science/api/pith-number/SMS45R55I7EMCH6TNAWHHYYZIK/graph.json","events_json":"https://pith.science/api/pith-number/SMS45R55I7EMCH6TNAWHHYYZIK/events.json","paper":"https://pith.science/paper/SMS45R55"},"agent_actions":{"view_html":"https://pith.science/pith/SMS45R55I7EMCH6TNAWHHYYZIK","download_json":"https://pith.science/pith/SMS45R55I7EMCH6TNAWHHYYZIK.json","view_paper":"https://pith.science/paper/SMS45R55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.07180&json=true","fetch_graph":"https://pith.science/api/pith-number/SMS45R55I7EMCH6TNAWHHYYZIK/graph.json","fetch_events":"https://pith.science/api/pith-number/SMS45R55I7EMCH6TNAWHHYYZIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMS45R55I7EMCH6TNAWHHYYZIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMS45R55I7EMCH6TNAWHHYYZIK/action/storage_attestation","attest_author":"https://pith.science/pith/SMS45R55I7EMCH6TNAWHHYYZIK/action/author_attestation","sign_citation":"https://pith.science/pith/SMS45R55I7EMCH6TNAWHHYYZIK/action/citation_signature","submit_replication":"https://pith.science/pith/SMS45R55I7EMCH6TNAWHHYYZIK/action/replication_record"}},"created_at":"2026-07-05T04:40:27.303929+00:00","updated_at":"2026-07-05T04:40:27.303929+00:00"}