{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NYIGKAOR5LNWTKJ6UDMY5L4UUP","short_pith_number":"pith:NYIGKAOR","schema_version":"1.0","canonical_sha256":"6e106501d1eadb69a93ea0d98eaf94a3c2b9c5eede9abcb56e6c0bd4b2670455","source":{"kind":"arxiv","id":"1909.12415","version":1},"attestation_state":"computed","paper":{"title":"Improving RNN Transducer Modeling for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Hu Hu, Jinyu Li, Rui Zhao, Yifan Gong","submitted_at":"2019-09-26T22:09:09Z","abstract_excerpt":"In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention Encoder-Decoder (AED), and RNN Transducer (RNN-T) are the most popular three methods. Among these three methods, RNN-T has the advantages to do online streaming which is challenging to AED and it doesn't have CTC's frame-independence assumption. In this paper, we improve the RNN-T training in two aspects. First, we optimize the training algorithm of RNN-T to reduce the memory consumption so that we can have larger tra"},"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":"1909.12415","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-26T22:09:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"b6e4bac75a1ae61180c4ab6d8e303271c1343ef9d0649173d5748cec15ccfd13","abstract_canon_sha256":"b5752848b19039dfb6da456aee7b194e74ab25d321bbbe7c29f94e0a1cc51b94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:39.427825Z","signature_b64":"oCxxfUaG2eIsJKtZjH7hzzN5XeZh6IIldNCBZzAMou+xD34bXTgSXQcgsepXX5Cgi/BqivFHokWGs0w1bE4hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e106501d1eadb69a93ea0d98eaf94a3c2b9c5eede9abcb56e6c0bd4b2670455","last_reissued_at":"2026-07-05T00:07:39.427391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:39.427391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving RNN Transducer Modeling for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Hu Hu, Jinyu Li, Rui Zhao, Yifan Gong","submitted_at":"2019-09-26T22:09:09Z","abstract_excerpt":"In the last few years, an emerging trend in automatic speech recognition research is the study of end-to-end (E2E) systems. Connectionist Temporal Classification (CTC), Attention Encoder-Decoder (AED), and RNN Transducer (RNN-T) are the most popular three methods. Among these three methods, RNN-T has the advantages to do online streaming which is challenging to AED and it doesn't have CTC's frame-independence assumption. In this paper, we improve the RNN-T training in two aspects. First, we optimize the training algorithm of RNN-T to reduce the memory consumption so that we can have larger tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12415","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/1909.12415/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":"1909.12415","created_at":"2026-07-05T00:07:39.427447+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.12415v1","created_at":"2026-07-05T00:07:39.427447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12415","created_at":"2026-07-05T00:07:39.427447+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYIGKAOR5LNW","created_at":"2026-07-05T00:07:39.427447+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYIGKAOR5LNWTKJ6","created_at":"2026-07-05T00:07:39.427447+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYIGKAOR","created_at":"2026-07-05T00:07:39.427447+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/NYIGKAOR5LNWTKJ6UDMY5L4UUP","json":"https://pith.science/pith/NYIGKAOR5LNWTKJ6UDMY5L4UUP.json","graph_json":"https://pith.science/api/pith-number/NYIGKAOR5LNWTKJ6UDMY5L4UUP/graph.json","events_json":"https://pith.science/api/pith-number/NYIGKAOR5LNWTKJ6UDMY5L4UUP/events.json","paper":"https://pith.science/paper/NYIGKAOR"},"agent_actions":{"view_html":"https://pith.science/pith/NYIGKAOR5LNWTKJ6UDMY5L4UUP","download_json":"https://pith.science/pith/NYIGKAOR5LNWTKJ6UDMY5L4UUP.json","view_paper":"https://pith.science/paper/NYIGKAOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.12415&json=true","fetch_graph":"https://pith.science/api/pith-number/NYIGKAOR5LNWTKJ6UDMY5L4UUP/graph.json","fetch_events":"https://pith.science/api/pith-number/NYIGKAOR5LNWTKJ6UDMY5L4UUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYIGKAOR5LNWTKJ6UDMY5L4UUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYIGKAOR5LNWTKJ6UDMY5L4UUP/action/storage_attestation","attest_author":"https://pith.science/pith/NYIGKAOR5LNWTKJ6UDMY5L4UUP/action/author_attestation","sign_citation":"https://pith.science/pith/NYIGKAOR5LNWTKJ6UDMY5L4UUP/action/citation_signature","submit_replication":"https://pith.science/pith/NYIGKAOR5LNWTKJ6UDMY5L4UUP/action/replication_record"}},"created_at":"2026-07-05T00:07:39.427447+00:00","updated_at":"2026-07-05T00:07:39.427447+00:00"}