{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HC6TJNKEAJ4LPYUWUAK4VFD3ZV","short_pith_number":"pith:HC6TJNKE","schema_version":"1.0","canonical_sha256":"38bd34b5440278b7e296a015ca947bcd76912d827d8a0fd51ebec0e9bc31ef16","source":{"kind":"arxiv","id":"2401.06788","version":2},"attestation_state":"computed","paper":{"title":"The NPU-ASLP-LiAuto System Description for Visual Speech Recognition in CNVSRC 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"He Wang, Lei Xie, Pan Zhou, Pengcheng Guo, Wei Chen","submitted_at":"2024-01-07T14:20:52Z","abstract_excerpt":"This paper delineates the visual speech recognition (VSR) system introduced by the NPU-ASLP-LiAuto (Team 237) in the first Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023, engaging in the fixed and open tracks of Single-Speaker VSR Task, and the open track of Multi-Speaker VSR Task. In terms of data processing, we leverage the lip motion extractor from the baseline1 to produce multi-scale video data. Besides, various augmentation techniques are applied during training, encompassing speed perturbation, random rotation, horizontal flipping, and color transformation. The VSR "},"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":"2401.06788","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-07T14:20:52Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"c75b9d661466f2e71dec1e241f7af7270208cf6043cec48a2c5d7ad3595f33d1","abstract_canon_sha256":"7a6ac34794331efd62a351616f28a5ee498f7b8edf60ddcf1d83cc8f75e2606f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:39.932108Z","signature_b64":"5cMxSVMPtqGjaMmzTRB77qDkXAKafs5IDh0yaa+u+uxUDJbRr1Ab1dB1j9OS8aHTVW9mUSjCvp43fVN3ujFWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38bd34b5440278b7e296a015ca947bcd76912d827d8a0fd51ebec0e9bc31ef16","last_reissued_at":"2026-07-05T07:50:39.931516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:39.931516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The NPU-ASLP-LiAuto System Description for Visual Speech Recognition in CNVSRC 2023","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"He Wang, Lei Xie, Pan Zhou, Pengcheng Guo, Wei Chen","submitted_at":"2024-01-07T14:20:52Z","abstract_excerpt":"This paper delineates the visual speech recognition (VSR) system introduced by the NPU-ASLP-LiAuto (Team 237) in the first Chinese Continuous Visual Speech Recognition Challenge (CNVSRC) 2023, engaging in the fixed and open tracks of Single-Speaker VSR Task, and the open track of Multi-Speaker VSR Task. In terms of data processing, we leverage the lip motion extractor from the baseline1 to produce multi-scale video data. Besides, various augmentation techniques are applied during training, encompassing speed perturbation, random rotation, horizontal flipping, and color transformation. The VSR "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06788","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/2401.06788/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":"2401.06788","created_at":"2026-07-05T07:50:39.931582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06788v2","created_at":"2026-07-05T07:50:39.931582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06788","created_at":"2026-07-05T07:50:39.931582+00:00"},{"alias_kind":"pith_short_12","alias_value":"HC6TJNKEAJ4L","created_at":"2026-07-05T07:50:39.931582+00:00"},{"alias_kind":"pith_short_16","alias_value":"HC6TJNKEAJ4LPYUW","created_at":"2026-07-05T07:50:39.931582+00:00"},{"alias_kind":"pith_short_8","alias_value":"HC6TJNKE","created_at":"2026-07-05T07:50:39.931582+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02010","citing_title":"CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HC6TJNKEAJ4LPYUWUAK4VFD3ZV","json":"https://pith.science/pith/HC6TJNKEAJ4LPYUWUAK4VFD3ZV.json","graph_json":"https://pith.science/api/pith-number/HC6TJNKEAJ4LPYUWUAK4VFD3ZV/graph.json","events_json":"https://pith.science/api/pith-number/HC6TJNKEAJ4LPYUWUAK4VFD3ZV/events.json","paper":"https://pith.science/paper/HC6TJNKE"},"agent_actions":{"view_html":"https://pith.science/pith/HC6TJNKEAJ4LPYUWUAK4VFD3ZV","download_json":"https://pith.science/pith/HC6TJNKEAJ4LPYUWUAK4VFD3ZV.json","view_paper":"https://pith.science/paper/HC6TJNKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06788&json=true","fetch_graph":"https://pith.science/api/pith-number/HC6TJNKEAJ4LPYUWUAK4VFD3ZV/graph.json","fetch_events":"https://pith.science/api/pith-number/HC6TJNKEAJ4LPYUWUAK4VFD3ZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HC6TJNKEAJ4LPYUWUAK4VFD3ZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HC6TJNKEAJ4LPYUWUAK4VFD3ZV/action/storage_attestation","attest_author":"https://pith.science/pith/HC6TJNKEAJ4LPYUWUAK4VFD3ZV/action/author_attestation","sign_citation":"https://pith.science/pith/HC6TJNKEAJ4LPYUWUAK4VFD3ZV/action/citation_signature","submit_replication":"https://pith.science/pith/HC6TJNKEAJ4LPYUWUAK4VFD3ZV/action/replication_record"}},"created_at":"2026-07-05T07:50:39.931582+00:00","updated_at":"2026-07-05T07:50:39.931582+00:00"}