{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BUZ3RWHVNFBHZGABEIS7TISB5T","short_pith_number":"pith:BUZ3RWHV","schema_version":"1.0","canonical_sha256":"0d33b8d8f569427c98012225f9a241ecc09d506dd4304913d534de44212c5b07","source":{"kind":"arxiv","id":"2002.05314","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised learning for audio-visual speaker diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Liqiang Wang, Shi-Xiong Zhang, Yahuan Cong, Yifan Ding, Yong Xu","submitted_at":"2020-02-13T02:36:32Z","abstract_excerpt":"Speaker diarization, which is to find the speech segments of specific speakers, has been widely used in human-centered applications such as video conferences or human-computer interaction systems. In this paper, we propose a self-supervised audio-video synchronization learning method to address the problem of speaker diarization without massive labeling effort. We improve the previous approaches by introducing two new loss functions: the dynamic triplet loss and the multinomial loss. We test them on a real-world human-computer interaction system and the results show our best model yields a rem"},"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":"2002.05314","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-02-13T02:36:32Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","stat.ML"],"title_canon_sha256":"c3e172a6a078964645bc9955c74c3ccd410e68c464187bbf55fd672a60cd9e6d","abstract_canon_sha256":"e92c42f4087918ee28a252adc9a982eb9fd072716e38a9c165078d317cf83837"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:40:30.120888Z","signature_b64":"l08Ph+P6IThYh9vAAyDUiqxL4ya2KAi1Q+zmiFlYK9UQUC6vd6JVF301RbAMrJ131LEZXNDvSh0N5Mp/8XIuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d33b8d8f569427c98012225f9a241ecc09d506dd4304913d534de44212c5b07","last_reissued_at":"2026-07-05T00:40:30.120507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:40:30.120507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised learning for audio-visual speaker diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Liqiang Wang, Shi-Xiong Zhang, Yahuan Cong, Yifan Ding, Yong Xu","submitted_at":"2020-02-13T02:36:32Z","abstract_excerpt":"Speaker diarization, which is to find the speech segments of specific speakers, has been widely used in human-centered applications such as video conferences or human-computer interaction systems. In this paper, we propose a self-supervised audio-video synchronization learning method to address the problem of speaker diarization without massive labeling effort. We improve the previous approaches by introducing two new loss functions: the dynamic triplet loss and the multinomial loss. We test them on a real-world human-computer interaction system and the results show our best model yields a rem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05314","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/2002.05314/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":"2002.05314","created_at":"2026-07-05T00:40:30.120563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05314v1","created_at":"2026-07-05T00:40:30.120563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05314","created_at":"2026-07-05T00:40:30.120563+00:00"},{"alias_kind":"pith_short_12","alias_value":"BUZ3RWHVNFBH","created_at":"2026-07-05T00:40:30.120563+00:00"},{"alias_kind":"pith_short_16","alias_value":"BUZ3RWHVNFBHZGAB","created_at":"2026-07-05T00:40:30.120563+00:00"},{"alias_kind":"pith_short_8","alias_value":"BUZ3RWHV","created_at":"2026-07-05T00:40:30.120563+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/BUZ3RWHVNFBHZGABEIS7TISB5T","json":"https://pith.science/pith/BUZ3RWHVNFBHZGABEIS7TISB5T.json","graph_json":"https://pith.science/api/pith-number/BUZ3RWHVNFBHZGABEIS7TISB5T/graph.json","events_json":"https://pith.science/api/pith-number/BUZ3RWHVNFBHZGABEIS7TISB5T/events.json","paper":"https://pith.science/paper/BUZ3RWHV"},"agent_actions":{"view_html":"https://pith.science/pith/BUZ3RWHVNFBHZGABEIS7TISB5T","download_json":"https://pith.science/pith/BUZ3RWHVNFBHZGABEIS7TISB5T.json","view_paper":"https://pith.science/paper/BUZ3RWHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05314&json=true","fetch_graph":"https://pith.science/api/pith-number/BUZ3RWHVNFBHZGABEIS7TISB5T/graph.json","fetch_events":"https://pith.science/api/pith-number/BUZ3RWHVNFBHZGABEIS7TISB5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BUZ3RWHVNFBHZGABEIS7TISB5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BUZ3RWHVNFBHZGABEIS7TISB5T/action/storage_attestation","attest_author":"https://pith.science/pith/BUZ3RWHVNFBHZGABEIS7TISB5T/action/author_attestation","sign_citation":"https://pith.science/pith/BUZ3RWHVNFBHZGABEIS7TISB5T/action/citation_signature","submit_replication":"https://pith.science/pith/BUZ3RWHVNFBHZGABEIS7TISB5T/action/replication_record"}},"created_at":"2026-07-05T00:40:30.120563+00:00","updated_at":"2026-07-05T00:40:30.120563+00:00"}