{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TIDO3KDLQCHY3Q7SSLJLZQFCUJ","short_pith_number":"pith:TIDO3KDL","schema_version":"1.0","canonical_sha256":"9a06eda86b808f8dc3f292d2bcc0a2a27de49c2b2097ba10a20b053c7bee6522","source":{"kind":"arxiv","id":"2211.09412","version":1},"attestation_state":"computed","paper":{"title":"LongFNT: Long-form Speech Recognition with Factorized Neural Transducer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinyu Li, Rui Zhao, Shujie Liu, Xie Chen, Xun Gong, Yanmin Qian, Yu Wu","submitted_at":"2022-11-17T08:48:27Z","abstract_excerpt":"Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer transcription history for a vanilla neural transducer model shows no much gain in our preliminary experiments, since the prediction network is not a pure language model. This motivates us to leverage the factorized neural transducer structure, containing a real language model, the vocabulary predictor. We propose the {LongFNT-Text} architecture, which fuses the 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":"2211.09412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-17T08:48:27Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"1b27a89de04e8956a532c39aaad1b295fc61793022faedb3ad1652223cbc4ba0","abstract_canon_sha256":"0c6f1163aebb7ec58af3786f7c15e8f05f080899a4dbf4898735a9f00999c54a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:55.733865Z","signature_b64":"KQGKPV+vtfNXB1bYBFhjRKFrETALXmYZFhqkl58tuWp+eu88+Qmdjo65F99lD3otmllDxbA5L6vKagrhy5ehCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a06eda86b808f8dc3f292d2bcc0a2a27de49c2b2097ba10a20b053c7bee6522","last_reissued_at":"2026-07-05T05:16:55.733476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:55.733476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LongFNT: Long-form Speech Recognition with Factorized Neural Transducer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinyu Li, Rui Zhao, Shujie Liu, Xie Chen, Xun Gong, Yanmin Qian, Yu Wu","submitted_at":"2022-11-17T08:48:27Z","abstract_excerpt":"Traditional automatic speech recognition~(ASR) systems usually focus on individual utterances, without considering long-form speech with useful historical information, which is more practical in real scenarios. Simply attending longer transcription history for a vanilla neural transducer model shows no much gain in our preliminary experiments, since the prediction network is not a pure language model. This motivates us to leverage the factorized neural transducer structure, containing a real language model, the vocabulary predictor. We propose the {LongFNT-Text} architecture, which fuses the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09412","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/2211.09412/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":"2211.09412","created_at":"2026-07-05T05:16:55.733534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09412v1","created_at":"2026-07-05T05:16:55.733534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09412","created_at":"2026-07-05T05:16:55.733534+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIDO3KDLQCHY","created_at":"2026-07-05T05:16:55.733534+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIDO3KDLQCHY3Q7S","created_at":"2026-07-05T05:16:55.733534+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIDO3KDL","created_at":"2026-07-05T05:16:55.733534+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/TIDO3KDLQCHY3Q7SSLJLZQFCUJ","json":"https://pith.science/pith/TIDO3KDLQCHY3Q7SSLJLZQFCUJ.json","graph_json":"https://pith.science/api/pith-number/TIDO3KDLQCHY3Q7SSLJLZQFCUJ/graph.json","events_json":"https://pith.science/api/pith-number/TIDO3KDLQCHY3Q7SSLJLZQFCUJ/events.json","paper":"https://pith.science/paper/TIDO3KDL"},"agent_actions":{"view_html":"https://pith.science/pith/TIDO3KDLQCHY3Q7SSLJLZQFCUJ","download_json":"https://pith.science/pith/TIDO3KDLQCHY3Q7SSLJLZQFCUJ.json","view_paper":"https://pith.science/paper/TIDO3KDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09412&json=true","fetch_graph":"https://pith.science/api/pith-number/TIDO3KDLQCHY3Q7SSLJLZQFCUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TIDO3KDLQCHY3Q7SSLJLZQFCUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIDO3KDLQCHY3Q7SSLJLZQFCUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIDO3KDLQCHY3Q7SSLJLZQFCUJ/action/storage_attestation","attest_author":"https://pith.science/pith/TIDO3KDLQCHY3Q7SSLJLZQFCUJ/action/author_attestation","sign_citation":"https://pith.science/pith/TIDO3KDLQCHY3Q7SSLJLZQFCUJ/action/citation_signature","submit_replication":"https://pith.science/pith/TIDO3KDLQCHY3Q7SSLJLZQFCUJ/action/replication_record"}},"created_at":"2026-07-05T05:16:55.733534+00:00","updated_at":"2026-07-05T05:16:55.733534+00:00"}