{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MNKK5GIMYSI3PA6WFOZOQTOV2S","short_pith_number":"pith:MNKK5GIM","schema_version":"1.0","canonical_sha256":"6354ae990cc491b783d62bb2e84dd5d4a2e38b403772bb36af65fdf39370e9db","source":{"kind":"arxiv","id":"2104.01721","version":1},"attestation_state":"computed","paper":{"title":"Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Jagadeesh Balam, Oleksii Hrinchuk, Somshubra Majumdar, Vahid Noroozi, Vitaly Lavrukhin","submitted_at":"2021-04-05T00:16:27Z","abstract_excerpt":"We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions combined with sub-word encoding and squeeze-and-excitation. The resulting architecture significantly reduces the gap between non-autoregressive and sequence-to-sequence and transducer models. We evaluate Citrinet on LibriSpeech, TED-LIUM2, AISHELL-1 and Multilingual LibriSpeech (MLS) English speech datasets. Citrinet accuracy on these datasets is close to the best"},"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":"2104.01721","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-05T00:16:27Z","cross_cats_sorted":[],"title_canon_sha256":"dd92314e3bab764a1f7d4911db76d4ef70d498055d227a655079120c2cc032e6","abstract_canon_sha256":"f237efe809e0ea52584dfa92aceab3ba9a4a73ba043a7d97dacdaf702f29c162"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:02.890429Z","signature_b64":"yMXDxZ9VOIFwM7QR/Pq3b+/MrBTkdgXLwfVIrMhDcPG47iwAuQeJZ9gUxZmBqh79b84wmEC8NlojKTERyioNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6354ae990cc491b783d62bb2e84dd5d4a2e38b403772bb36af65fdf39370e9db","last_reissued_at":"2026-07-05T02:29:02.890049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:02.890049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Jagadeesh Balam, Oleksii Hrinchuk, Somshubra Majumdar, Vahid Noroozi, Vitaly Lavrukhin","submitted_at":"2021-04-05T00:16:27Z","abstract_excerpt":"We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions combined with sub-word encoding and squeeze-and-excitation. The resulting architecture significantly reduces the gap between non-autoregressive and sequence-to-sequence and transducer models. We evaluate Citrinet on LibriSpeech, TED-LIUM2, AISHELL-1 and Multilingual LibriSpeech (MLS) English speech datasets. Citrinet accuracy on these datasets is close to the best"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01721","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/2104.01721/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":"2104.01721","created_at":"2026-07-05T02:29:02.890109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01721v1","created_at":"2026-07-05T02:29:02.890109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01721","created_at":"2026-07-05T02:29:02.890109+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNKK5GIMYSI3","created_at":"2026-07-05T02:29:02.890109+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNKK5GIMYSI3PA6W","created_at":"2026-07-05T02:29:02.890109+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNKK5GIM","created_at":"2026-07-05T02:29:02.890109+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/MNKK5GIMYSI3PA6WFOZOQTOV2S","json":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S.json","graph_json":"https://pith.science/api/pith-number/MNKK5GIMYSI3PA6WFOZOQTOV2S/graph.json","events_json":"https://pith.science/api/pith-number/MNKK5GIMYSI3PA6WFOZOQTOV2S/events.json","paper":"https://pith.science/paper/MNKK5GIM"},"agent_actions":{"view_html":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S","download_json":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S.json","view_paper":"https://pith.science/paper/MNKK5GIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01721&json=true","fetch_graph":"https://pith.science/api/pith-number/MNKK5GIMYSI3PA6WFOZOQTOV2S/graph.json","fetch_events":"https://pith.science/api/pith-number/MNKK5GIMYSI3PA6WFOZOQTOV2S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/action/storage_attestation","attest_author":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/action/author_attestation","sign_citation":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/action/citation_signature","submit_replication":"https://pith.science/pith/MNKK5GIMYSI3PA6WFOZOQTOV2S/action/replication_record"}},"created_at":"2026-07-05T02:29:02.890109+00:00","updated_at":"2026-07-05T02:29:02.890109+00:00"}