{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2QRRNWV3LQQ3FZ2UUXG6ZJRV35","short_pith_number":"pith:2QRRNWV3","schema_version":"1.0","canonical_sha256":"d42316dabb5c21b2e754a5cdeca635df6357699890efe6c5ef75bb170f411d32","source":{"kind":"arxiv","id":"2303.00628","version":2},"attestation_state":"computed","paper":{"title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Bowen Shi, Changhan Wang, Juan Pino, Mohamed Anwar, Vedanuj Goswami, Wei-Ning Hsu","submitted_at":"2023-03-01T16:31:01Z","abstract_excerpt":"We introduce MuAViC, a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation providing 1200 hours of audio-visual speech in 9 languages. It is fully transcribed and covers 6 English-to-X translation as well as 6 X-to-English translation directions. To the best of our knowledge, this is the first open benchmark for audio-visual speech-to-text translation and the largest open benchmark for multilingual audio-visual speech recognition. Our baseline results show that MuAViC is effective for building noise-robust speech recognition and translation mode"},"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":"2303.00628","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-01T16:31:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"bc30bb878453577c3072dbe052d16ebf51febd04e9e5d4e13c03f7da18404b12","abstract_canon_sha256":"d2afb16f9f435f891a0efbb569eeabe0f8b45e1473d28a992dbc622882d7588f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:53.629560Z","signature_b64":"mYIBXeanqWtCM9N+qfH1hOjt9D6w0dSmRvMaT4tIhP6uieSbba9wIKvQICoxaLkVWfacVUE7ESvGo8c2CYSWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d42316dabb5c21b2e754a5cdeca635df6357699890efe6c5ef75bb170f411d32","last_reissued_at":"2026-07-05T05:48:53.629116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:53.629116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Bowen Shi, Changhan Wang, Juan Pino, Mohamed Anwar, Vedanuj Goswami, Wei-Ning Hsu","submitted_at":"2023-03-01T16:31:01Z","abstract_excerpt":"We introduce MuAViC, a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation providing 1200 hours of audio-visual speech in 9 languages. It is fully transcribed and covers 6 English-to-X translation as well as 6 X-to-English translation directions. To the best of our knowledge, this is the first open benchmark for audio-visual speech-to-text translation and the largest open benchmark for multilingual audio-visual speech recognition. Our baseline results show that MuAViC is effective for building noise-robust speech recognition and translation mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00628","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/2303.00628/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":"2303.00628","created_at":"2026-07-05T05:48:53.629173+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00628v2","created_at":"2026-07-05T05:48:53.629173+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00628","created_at":"2026-07-05T05:48:53.629173+00:00"},{"alias_kind":"pith_short_12","alias_value":"2QRRNWV3LQQ3","created_at":"2026-07-05T05:48:53.629173+00:00"},{"alias_kind":"pith_short_16","alias_value":"2QRRNWV3LQQ3FZ2U","created_at":"2026-07-05T05:48:53.629173+00:00"},{"alias_kind":"pith_short_8","alias_value":"2QRRNWV3","created_at":"2026-07-05T05:48:53.629173+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05763","citing_title":"M2S-AVSR: Modality-aware Multi-view Self-supervised Representation for Robust Audio-Visual Speech Recognition","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05591","citing_title":"AI-Driven Modular Services for Accessible Multilingual Education in Immersive Extended Reality Settings: Integrating Speech Processing, Translation, and Sign Language Rendering","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2QRRNWV3LQQ3FZ2UUXG6ZJRV35","json":"https://pith.science/pith/2QRRNWV3LQQ3FZ2UUXG6ZJRV35.json","graph_json":"https://pith.science/api/pith-number/2QRRNWV3LQQ3FZ2UUXG6ZJRV35/graph.json","events_json":"https://pith.science/api/pith-number/2QRRNWV3LQQ3FZ2UUXG6ZJRV35/events.json","paper":"https://pith.science/paper/2QRRNWV3"},"agent_actions":{"view_html":"https://pith.science/pith/2QRRNWV3LQQ3FZ2UUXG6ZJRV35","download_json":"https://pith.science/pith/2QRRNWV3LQQ3FZ2UUXG6ZJRV35.json","view_paper":"https://pith.science/paper/2QRRNWV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00628&json=true","fetch_graph":"https://pith.science/api/pith-number/2QRRNWV3LQQ3FZ2UUXG6ZJRV35/graph.json","fetch_events":"https://pith.science/api/pith-number/2QRRNWV3LQQ3FZ2UUXG6ZJRV35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2QRRNWV3LQQ3FZ2UUXG6ZJRV35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2QRRNWV3LQQ3FZ2UUXG6ZJRV35/action/storage_attestation","attest_author":"https://pith.science/pith/2QRRNWV3LQQ3FZ2UUXG6ZJRV35/action/author_attestation","sign_citation":"https://pith.science/pith/2QRRNWV3LQQ3FZ2UUXG6ZJRV35/action/citation_signature","submit_replication":"https://pith.science/pith/2QRRNWV3LQQ3FZ2UUXG6ZJRV35/action/replication_record"}},"created_at":"2026-07-05T05:48:53.629173+00:00","updated_at":"2026-07-05T05:48:53.629173+00:00"}