{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7TQBLM62OMRVXIF7VUVQQI4FB5","short_pith_number":"pith:7TQBLM62","schema_version":"1.0","canonical_sha256":"fce015b3da73235ba0bfad2b0823850f68cf550e0aa4233b2f37fb8ef1376995","source":{"kind":"arxiv","id":"2403.13423","version":1},"attestation_state":"computed","paper":{"title":"Advanced Long-Content Speech Recognition With Factorized Neural Transducer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinyu Li, Rui Zhao, Shujie Liu, Xie Chen, Xun Gong, Yanmin Qian, Yu Wu","submitted_at":"2024-03-20T09:09:49Z","abstract_excerpt":"In this paper, we propose two novel approaches, which integrate long-content information into the factorized neural transducer (FNT) based architecture in both non-streaming (referred to as LongFNT ) and streaming (referred to as SLongFNT ) scenarios. We first investigate whether long-content transcriptions can improve the vanilla conformer transducer (C-T) models. Our experiments indicate that the vanilla C-T models do not exhibit improved performance when utilizing long-content transcriptions, possibly due to the predictor network of C-T models not functioning as a pure language model. Inste"},"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":"2403.13423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-20T09:09:49Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f1a7c49a2b2fd4ed2b75b3490383a5ee36eabe703258197adc7c7b2cef0fa7a6","abstract_canon_sha256":"2817d157012fa34df7a0ecd5179a10f6dac17429ebf0749386d5c895073ce59f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:36.387606Z","signature_b64":"cu/qkycHJOTfQfxGWw2u6WCSRcca+p3+WwBwsOY7H4cfZoKefAkVgTU5oETgsPZP0/QYer0cV6oXsvDsw/8NBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fce015b3da73235ba0bfad2b0823850f68cf550e0aa4233b2f37fb8ef1376995","last_reissued_at":"2026-07-05T07:58:36.387099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:36.387099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advanced Long-Content Speech Recognition With Factorized Neural Transducer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinyu Li, Rui Zhao, Shujie Liu, Xie Chen, Xun Gong, Yanmin Qian, Yu Wu","submitted_at":"2024-03-20T09:09:49Z","abstract_excerpt":"In this paper, we propose two novel approaches, which integrate long-content information into the factorized neural transducer (FNT) based architecture in both non-streaming (referred to as LongFNT ) and streaming (referred to as SLongFNT ) scenarios. We first investigate whether long-content transcriptions can improve the vanilla conformer transducer (C-T) models. Our experiments indicate that the vanilla C-T models do not exhibit improved performance when utilizing long-content transcriptions, possibly due to the predictor network of C-T models not functioning as a pure language model. Inste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13423","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/2403.13423/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":"2403.13423","created_at":"2026-07-05T07:58:36.387162+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13423v1","created_at":"2026-07-05T07:58:36.387162+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13423","created_at":"2026-07-05T07:58:36.387162+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TQBLM62OMRV","created_at":"2026-07-05T07:58:36.387162+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TQBLM62OMRVXIF7","created_at":"2026-07-05T07:58:36.387162+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TQBLM62","created_at":"2026-07-05T07:58:36.387162+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/7TQBLM62OMRVXIF7VUVQQI4FB5","json":"https://pith.science/pith/7TQBLM62OMRVXIF7VUVQQI4FB5.json","graph_json":"https://pith.science/api/pith-number/7TQBLM62OMRVXIF7VUVQQI4FB5/graph.json","events_json":"https://pith.science/api/pith-number/7TQBLM62OMRVXIF7VUVQQI4FB5/events.json","paper":"https://pith.science/paper/7TQBLM62"},"agent_actions":{"view_html":"https://pith.science/pith/7TQBLM62OMRVXIF7VUVQQI4FB5","download_json":"https://pith.science/pith/7TQBLM62OMRVXIF7VUVQQI4FB5.json","view_paper":"https://pith.science/paper/7TQBLM62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13423&json=true","fetch_graph":"https://pith.science/api/pith-number/7TQBLM62OMRVXIF7VUVQQI4FB5/graph.json","fetch_events":"https://pith.science/api/pith-number/7TQBLM62OMRVXIF7VUVQQI4FB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TQBLM62OMRVXIF7VUVQQI4FB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TQBLM62OMRVXIF7VUVQQI4FB5/action/storage_attestation","attest_author":"https://pith.science/pith/7TQBLM62OMRVXIF7VUVQQI4FB5/action/author_attestation","sign_citation":"https://pith.science/pith/7TQBLM62OMRVXIF7VUVQQI4FB5/action/citation_signature","submit_replication":"https://pith.science/pith/7TQBLM62OMRVXIF7VUVQQI4FB5/action/replication_record"}},"created_at":"2026-07-05T07:58:36.387162+00:00","updated_at":"2026-07-05T07:58:36.387162+00:00"}