{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5TJYZUBBH6MZJZY2O26DCUXSHR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"59489636095a511f54e6ccf6dba3b19da8ad2ce08719c46b6972fa12d5eb7472","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-01-06T16:43:05Z","title_canon_sha256":"c40701c0875c1a07ffe8f9b7ddf426c19ad62f375613c696a39f9377dd613cd3"},"schema_version":"1.0","source":{"id":"2001.01656","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.01656","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"arxiv_version","alias_value":"2001.01656v1","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.01656","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"pith_short_12","alias_value":"5TJYZUBBH6MZ","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"pith_short_16","alias_value":"5TJYZUBBH6MZJZY2","created_at":"2026-07-05T00:29:48Z"},{"alias_kind":"pith_short_8","alias_value":"5TJYZUBB","created_at":"2026-07-05T00:29:48Z"}],"graph_snapshots":[{"event_id":"sha256:709c903b5f131a9632f95f444f54a0922983d7712e4bedd6687821a4ab6b5a25","target":"graph","created_at":"2026-07-05T00:29:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2001.01656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Wu, Dong Yu, Helen Meng, Jianwei Yu, Jian Wu, Shahram Ghorbani, Shansong Liu, Shi-Xiong Zhang, Shiyin Kang, Xunying Liu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-01-06T16:43:05Z","title":"Audio-visual Recognition of Overlapped speech for the LRS2 dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.01656","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a971c0e9534a634c68647d28350d6bc25fd1923b075a4804a3ac42ed08ef955c","target":"record","created_at":"2026-07-05T00:29:48Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"59489636095a511f54e6ccf6dba3b19da8ad2ce08719c46b6972fa12d5eb7472","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-01-06T16:43:05Z","title_canon_sha256":"c40701c0875c1a07ffe8f9b7ddf426c19ad62f375613c696a39f9377dd613cd3"},"schema_version":"1.0","source":{"id":"2001.01656","kind":"arxiv","version":1}},"canonical_sha256":"ecd38cd0213f9994e71a76bc3152f23c4c1ed4b254fa7f4af9bc27366b2141c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecd38cd0213f9994e71a76bc3152f23c4c1ed4b254fa7f4af9bc27366b2141c8","first_computed_at":"2026-07-05T00:29:48.810955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:29:48.810955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fg/ETjiIC78re9w9qHcrTUxtaKWb2T7x4LZTUmrE3lwch/GmTKDX56EdB5jUxAWcyziCV1OqZ+MYF93TyVtWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:29:48.811338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.01656","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a971c0e9534a634c68647d28350d6bc25fd1923b075a4804a3ac42ed08ef955c","sha256:709c903b5f131a9632f95f444f54a0922983d7712e4bedd6687821a4ab6b5a25"],"state_sha256":"d41daef0661c02615dbb136d89d7798a41ac2fb4e39d400442878a78686a4a8d"}