{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SNL65K7MECPJOBS2DDOLFPVORW","short_pith_number":"pith:SNL65K7M","schema_version":"1.0","canonical_sha256":"9357eeabec209e97065a18dcb2beae8d9d6d3719221ac6bf5ba49f88645b3bff","source":{"kind":"arxiv","id":"2303.06341","version":1},"attestation_state":"computed","paper":{"title":"The NPU-ASLP System for Audio-Visual Speech Recognition in MISP 2022 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ao Zhang, Bingshen Mu, He Wang, Peikun Chen, Pengcheng Guo","submitted_at":"2023-03-11T08:10:31Z","abstract_excerpt":"This paper describes our NPU-ASLP system for the Audio-Visual Diarization and Recognition (AVDR) task in the Multi-modal Information based Speech Processing (MISP) 2022 Challenge. Specifically, the weighted prediction error (WPE) and guided source separation (GSS) techniques are used to reduce reverberation and generate clean signals for each single speaker first. Then, we explore the effectiveness of Branchformer and E-Branchformer based ASR systems. To better make use of the visual modality, a cross-attention based multi-modal fusion module is proposed, which explicitly learns the contextual"},"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":"2303.06341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-11T08:10:31Z","cross_cats_sorted":[],"title_canon_sha256":"48e13096ae210ebb7db1b3305cdea8b534bf1907af795146f2e6239ac8d49d60","abstract_canon_sha256":"9fa7b02b8c177fe5f8d62d7b6a98f7fb52db2ba226ac3c295e2014d6dff264bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:17.591285Z","signature_b64":"KwToQsE8DeebFCF7NhwhUG17Ua9gvI6WXkNwZFvyfGJ92UX3WH3FRdlExI4b27DfMI47gq9cBZZCLP1lWms5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9357eeabec209e97065a18dcb2beae8d9d6d3719221ac6bf5ba49f88645b3bff","last_reissued_at":"2026-07-05T05:50:17.590877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:17.590877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The NPU-ASLP System for Audio-Visual Speech Recognition in MISP 2022 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ao Zhang, Bingshen Mu, He Wang, Peikun Chen, Pengcheng Guo","submitted_at":"2023-03-11T08:10:31Z","abstract_excerpt":"This paper describes our NPU-ASLP system for the Audio-Visual Diarization and Recognition (AVDR) task in the Multi-modal Information based Speech Processing (MISP) 2022 Challenge. Specifically, the weighted prediction error (WPE) and guided source separation (GSS) techniques are used to reduce reverberation and generate clean signals for each single speaker first. Then, we explore the effectiveness of Branchformer and E-Branchformer based ASR systems. To better make use of the visual modality, a cross-attention based multi-modal fusion module is proposed, which explicitly learns the contextual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06341","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/2303.06341/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":"2303.06341","created_at":"2026-07-05T05:50:17.590936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.06341v1","created_at":"2026-07-05T05:50:17.590936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06341","created_at":"2026-07-05T05:50:17.590936+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNL65K7MECPJ","created_at":"2026-07-05T05:50:17.590936+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNL65K7MECPJOBS2","created_at":"2026-07-05T05:50:17.590936+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNL65K7M","created_at":"2026-07-05T05:50:17.590936+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/SNL65K7MECPJOBS2DDOLFPVORW","json":"https://pith.science/pith/SNL65K7MECPJOBS2DDOLFPVORW.json","graph_json":"https://pith.science/api/pith-number/SNL65K7MECPJOBS2DDOLFPVORW/graph.json","events_json":"https://pith.science/api/pith-number/SNL65K7MECPJOBS2DDOLFPVORW/events.json","paper":"https://pith.science/paper/SNL65K7M"},"agent_actions":{"view_html":"https://pith.science/pith/SNL65K7MECPJOBS2DDOLFPVORW","download_json":"https://pith.science/pith/SNL65K7MECPJOBS2DDOLFPVORW.json","view_paper":"https://pith.science/paper/SNL65K7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.06341&json=true","fetch_graph":"https://pith.science/api/pith-number/SNL65K7MECPJOBS2DDOLFPVORW/graph.json","fetch_events":"https://pith.science/api/pith-number/SNL65K7MECPJOBS2DDOLFPVORW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNL65K7MECPJOBS2DDOLFPVORW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNL65K7MECPJOBS2DDOLFPVORW/action/storage_attestation","attest_author":"https://pith.science/pith/SNL65K7MECPJOBS2DDOLFPVORW/action/author_attestation","sign_citation":"https://pith.science/pith/SNL65K7MECPJOBS2DDOLFPVORW/action/citation_signature","submit_replication":"https://pith.science/pith/SNL65K7MECPJOBS2DDOLFPVORW/action/replication_record"}},"created_at":"2026-07-05T05:50:17.590936+00:00","updated_at":"2026-07-05T05:50:17.590936+00:00"}