{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XJQFS3MORGHBSBQ2GCP6U5DMQA","short_pith_number":"pith:XJQFS3MO","schema_version":"1.0","canonical_sha256":"ba60596d8e898e19061a309fea746c800d44d5c2122798f06a9cc473f03d6d71","source":{"kind":"arxiv","id":"2211.02133","version":2},"attestation_state":"computed","paper":{"title":"Streaming Audio-Visual Speech Recognition with Alignment Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Christian Fuegen, Maja Pantic, Niko Moritz, Pingchuan Ma, Stavros Petridis","submitted_at":"2022-11-03T20:20:47Z","abstract_excerpt":"In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer architecture, which is made streamable using chunk-wise self-attention (CSA) and causal convolution. Streaming recognition with a decoder neural network is realized by using the triggered attention technique, which performs time-synchronous decoding with joint CTC/attention scoring. Additionally, we propose a novel alignment regularization technique that promotes s"},"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":"2211.02133","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-03T20:20:47Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"6ae4aab2431c458cae813af67aff51a7418284849be902e236ff9589afc4d19b","abstract_canon_sha256":"0fdf7bbbc993677b26be57333a30a0f446e03e44eb4cc760b64e1116dea20de4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:43.903935Z","signature_b64":"fsm/bAu7a1qGozyGyCVIRra1QaPbLLzQ/ZVq1YfoBl9CZ7zOHMuX9kPzx1Ip0oCoCZJBH2+HK8EDj16WKnEjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba60596d8e898e19061a309fea746c800d44d5c2122798f06a9cc473f03d6d71","last_reissued_at":"2026-07-05T06:26:43.903455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:43.903455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Audio-Visual Speech Recognition with Alignment Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Christian Fuegen, Maja Pantic, Niko Moritz, Pingchuan Ma, Stavros Petridis","submitted_at":"2022-11-03T20:20:47Z","abstract_excerpt":"In this work, we propose a streaming AV-ASR system based on a hybrid connectionist temporal classification (CTC)/attention neural network architecture. The audio and the visual encoder neural networks are both based on the conformer architecture, which is made streamable using chunk-wise self-attention (CSA) and causal convolution. Streaming recognition with a decoder neural network is realized by using the triggered attention technique, which performs time-synchronous decoding with joint CTC/attention scoring. Additionally, we propose a novel alignment regularization technique that promotes s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02133","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/2211.02133/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":"2211.02133","created_at":"2026-07-05T06:26:43.903508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02133v2","created_at":"2026-07-05T06:26:43.903508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02133","created_at":"2026-07-05T06:26:43.903508+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJQFS3MORGHB","created_at":"2026-07-05T06:26:43.903508+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJQFS3MORGHBSBQ2","created_at":"2026-07-05T06:26:43.903508+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJQFS3MO","created_at":"2026-07-05T06:26:43.903508+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/XJQFS3MORGHBSBQ2GCP6U5DMQA","json":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA.json","graph_json":"https://pith.science/api/pith-number/XJQFS3MORGHBSBQ2GCP6U5DMQA/graph.json","events_json":"https://pith.science/api/pith-number/XJQFS3MORGHBSBQ2GCP6U5DMQA/events.json","paper":"https://pith.science/paper/XJQFS3MO"},"agent_actions":{"view_html":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA","download_json":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA.json","view_paper":"https://pith.science/paper/XJQFS3MO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02133&json=true","fetch_graph":"https://pith.science/api/pith-number/XJQFS3MORGHBSBQ2GCP6U5DMQA/graph.json","fetch_events":"https://pith.science/api/pith-number/XJQFS3MORGHBSBQ2GCP6U5DMQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/action/storage_attestation","attest_author":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/action/author_attestation","sign_citation":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/action/citation_signature","submit_replication":"https://pith.science/pith/XJQFS3MORGHBSBQ2GCP6U5DMQA/action/replication_record"}},"created_at":"2026-07-05T06:26:43.903508+00:00","updated_at":"2026-07-05T06:26:43.903508+00:00"}