{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5TJYZUBBH6MZJZY2O26DCUXSHR","short_pith_number":"pith:5TJYZUBB","schema_version":"1.0","canonical_sha256":"ecd38cd0213f9994e71a76bc3152f23c4c1ed4b254fa7f4af9bc27366b2141c8","source":{"kind":"arxiv","id":"2001.01656","version":1},"attestation_state":"computed","paper":{"title":"Audio-visual Recognition of Overlapped speech for the LRS2 dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo Wu, Dong Yu, Helen Meng, Jianwei Yu, Jian Wu, Shahram Ghorbani, Shansong Liu, Shi-Xiong Zhang, Shiyin Kang, Xunying Liu","submitted_at":"2020-01-06T16:43:05Z","abstract_excerpt":"Automatic recognition of overlapped speech remains a highly challenging task to date. Motivated by the bimodal nature of human speech perception, this paper investigates the use of audio-visual technologies for overlapped speech recognition. Three issues associated with the construction of audio-visual speech recognition (AVSR) systems are addressed. First, the basic architecture designs i.e. end-to-end and hybrid of AVSR systems are investigated. Second, purposefully designed modality fusion gates are used to robustly integrate the audio and visual features. Third, in contrast to a traditiona"},"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":"2001.01656","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-01-06T16:43:05Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"c40701c0875c1a07ffe8f9b7ddf426c19ad62f375613c696a39f9377dd613cd3","abstract_canon_sha256":"59489636095a511f54e6ccf6dba3b19da8ad2ce08719c46b6972fa12d5eb7472"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:48.811338Z","signature_b64":"Fg/ETjiIC78re9w9qHcrTUxtaKWb2T7x4LZTUmrE3lwch/GmTKDX56EdB5jUxAWcyziCV1OqZ+MYF93TyVtWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecd38cd0213f9994e71a76bc3152f23c4c1ed4b254fa7f4af9bc27366b2141c8","last_reissued_at":"2026-07-05T00:29:48.810955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:48.810955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio-visual Recognition of Overlapped speech for the LRS2 dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo Wu, Dong Yu, Helen Meng, Jianwei Yu, Jian Wu, Shahram Ghorbani, Shansong Liu, Shi-Xiong Zhang, Shiyin Kang, Xunying Liu","submitted_at":"2020-01-06T16:43:05Z","abstract_excerpt":"Automatic recognition of overlapped speech remains a highly challenging task to date. Motivated by the bimodal nature of human speech perception, this paper investigates the use of audio-visual technologies for overlapped speech recognition. Three issues associated with the construction of audio-visual speech recognition (AVSR) systems are addressed. First, the basic architecture designs i.e. end-to-end and hybrid of AVSR systems are investigated. Second, purposefully designed modality fusion gates are used to robustly integrate the audio and visual features. Third, in contrast to a traditiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.01656","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/2001.01656/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":"2001.01656","created_at":"2026-07-05T00:29:48.811019+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.01656v1","created_at":"2026-07-05T00:29:48.811019+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.01656","created_at":"2026-07-05T00:29:48.811019+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TJYZUBBH6MZ","created_at":"2026-07-05T00:29:48.811019+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TJYZUBBH6MZJZY2","created_at":"2026-07-05T00:29:48.811019+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TJYZUBB","created_at":"2026-07-05T00:29:48.811019+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/5TJYZUBBH6MZJZY2O26DCUXSHR","json":"https://pith.science/pith/5TJYZUBBH6MZJZY2O26DCUXSHR.json","graph_json":"https://pith.science/api/pith-number/5TJYZUBBH6MZJZY2O26DCUXSHR/graph.json","events_json":"https://pith.science/api/pith-number/5TJYZUBBH6MZJZY2O26DCUXSHR/events.json","paper":"https://pith.science/paper/5TJYZUBB"},"agent_actions":{"view_html":"https://pith.science/pith/5TJYZUBBH6MZJZY2O26DCUXSHR","download_json":"https://pith.science/pith/5TJYZUBBH6MZJZY2O26DCUXSHR.json","view_paper":"https://pith.science/paper/5TJYZUBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.01656&json=true","fetch_graph":"https://pith.science/api/pith-number/5TJYZUBBH6MZJZY2O26DCUXSHR/graph.json","fetch_events":"https://pith.science/api/pith-number/5TJYZUBBH6MZJZY2O26DCUXSHR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TJYZUBBH6MZJZY2O26DCUXSHR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TJYZUBBH6MZJZY2O26DCUXSHR/action/storage_attestation","attest_author":"https://pith.science/pith/5TJYZUBBH6MZJZY2O26DCUXSHR/action/author_attestation","sign_citation":"https://pith.science/pith/5TJYZUBBH6MZJZY2O26DCUXSHR/action/citation_signature","submit_replication":"https://pith.science/pith/5TJYZUBBH6MZJZY2O26DCUXSHR/action/replication_record"}},"created_at":"2026-07-05T00:29:48.811019+00:00","updated_at":"2026-07-05T00:29:48.811019+00:00"}