{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4FQXNLIV6QCDMHPCU2LDVON4LL","short_pith_number":"pith:4FQXNLIV","schema_version":"1.0","canonical_sha256":"e16176ad15f404361de2a6963ab9bc5aed91c40cf5f495cef532725e72234c17","source":{"kind":"arxiv","id":"2011.04084","version":1},"attestation_state":"computed","paper":{"title":"Listen, Look and Deliberate: Visual context-aware speech recognition using pre-trained text-video representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Jinyu Li, Shahram Ghorbani, Yashesh Gaur, Yu Shi","submitted_at":"2020-11-08T21:26:17Z","abstract_excerpt":"In this study, we try to address the problem of leveraging visual signals to improve Automatic Speech Recognition (ASR), also known as visual context-aware ASR (VC-ASR). We explore novel VC-ASR approaches to leverage video and text representations extracted by a self-supervised pre-trained text-video embedding model. Firstly, we propose a multi-stream attention architecture to leverage signals from both audio and video modalities. This architecture consists of separate encoders for the two modalities and a single decoder that attends over them. We show that this architecture is better than fus"},"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":"2011.04084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-11-08T21:26:17Z","cross_cats_sorted":["cs.SD","eess.IV"],"title_canon_sha256":"9b3df93cc9552e6d45ad86594c2a8135541ec8ef8ccff1ef1f91a8cb48a069f4","abstract_canon_sha256":"a118e201316b6914278956e13b456f66fdde2a3cb3a84430e752674ab53ecbb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:02.230858Z","signature_b64":"fGnA9tfGrCi+qPprjU8yhFANO7cZvXrIhchO8gxEC0L6rR3WP/QsP1+dm5v9MA9+HYi16rG2YwVG+FGVC4VWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e16176ad15f404361de2a6963ab9bc5aed91c40cf5f495cef532725e72234c17","last_reissued_at":"2026-07-05T01:50:02.230478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:02.230478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Listen, Look and Deliberate: Visual context-aware speech recognition using pre-trained text-video representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Jinyu Li, Shahram Ghorbani, Yashesh Gaur, Yu Shi","submitted_at":"2020-11-08T21:26:17Z","abstract_excerpt":"In this study, we try to address the problem of leveraging visual signals to improve Automatic Speech Recognition (ASR), also known as visual context-aware ASR (VC-ASR). We explore novel VC-ASR approaches to leverage video and text representations extracted by a self-supervised pre-trained text-video embedding model. Firstly, we propose a multi-stream attention architecture to leverage signals from both audio and video modalities. This architecture consists of separate encoders for the two modalities and a single decoder that attends over them. We show that this architecture is better than fus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04084","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/2011.04084/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":"2011.04084","created_at":"2026-07-05T01:50:02.230528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.04084v1","created_at":"2026-07-05T01:50:02.230528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04084","created_at":"2026-07-05T01:50:02.230528+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FQXNLIV6QCD","created_at":"2026-07-05T01:50:02.230528+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FQXNLIV6QCDMHPC","created_at":"2026-07-05T01:50:02.230528+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FQXNLIV","created_at":"2026-07-05T01:50:02.230528+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/4FQXNLIV6QCDMHPCU2LDVON4LL","json":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL.json","graph_json":"https://pith.science/api/pith-number/4FQXNLIV6QCDMHPCU2LDVON4LL/graph.json","events_json":"https://pith.science/api/pith-number/4FQXNLIV6QCDMHPCU2LDVON4LL/events.json","paper":"https://pith.science/paper/4FQXNLIV"},"agent_actions":{"view_html":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL","download_json":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL.json","view_paper":"https://pith.science/paper/4FQXNLIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.04084&json=true","fetch_graph":"https://pith.science/api/pith-number/4FQXNLIV6QCDMHPCU2LDVON4LL/graph.json","fetch_events":"https://pith.science/api/pith-number/4FQXNLIV6QCDMHPCU2LDVON4LL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/action/storage_attestation","attest_author":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/action/author_attestation","sign_citation":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/action/citation_signature","submit_replication":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/action/replication_record"}},"created_at":"2026-07-05T01:50:02.230528+00:00","updated_at":"2026-07-05T01:50:02.230528+00:00"}