{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HRSDJOZWMQWPA3GX7GSOXHZFLF","short_pith_number":"pith:HRSDJOZW","schema_version":"1.0","canonical_sha256":"3c6434bb36642cf06cd7f9a4eb9f25597462cbfa1eaafb661b523ca263a1779e","source":{"kind":"arxiv","id":"1707.07413","version":1},"attestation_state":"computed","paper":{"title":"Exploring Neural Transducers for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Adam Coates, Anuroop Sriram, David Seetapun, Eric Battenberg, Hairong Liu, Jitong Chen, Rewon Child, Sanjeev Satheesh, Yashesh Gaur, Yi Li, Zhenyao Zhu","submitted_at":"2017-07-24T06:05:21Z","abstract_excerpt":"In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition. We show that, without any language model, Seq2Seq and RNN-Transducer models both outperform the best reported CTC models with a language model, on the popular Hub5'00 benchmark. On our internal diverse dataset, these trends continue - RNNTransducer models rescored with a language model after beam search outperform our best CTC models. These results simplify the speech recognition pipeline so that decoding can now be expressed purely as neural net"},"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":"1707.07413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-24T06:05:21Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"a576a34991924c9817bd62f81bd039e0ac8d522f8f4a9a22c39d030c2ede24f9","abstract_canon_sha256":"897f5b4c86b18d89e8597e73f9fae49e2db2cba1d133c84f44b5bbf23c008059"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:42.311378Z","signature_b64":"TPOhMuDWOKPrrQWuwQqkCgWnVPqFlKa2DZ9/xULpBzafqedh8LFs/AOoDPKAZCIqRpTJDpVh3xQXuEkzi0nfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c6434bb36642cf06cd7f9a4eb9f25597462cbfa1eaafb661b523ca263a1779e","last_reissued_at":"2026-05-18T00:39:42.310693Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:42.310693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Neural Transducers for End-to-End Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.CL","authors_text":"Adam Coates, Anuroop Sriram, David Seetapun, Eric Battenberg, Hairong Liu, Jitong Chen, Rewon Child, Sanjeev Satheesh, Yashesh Gaur, Yi Li, Zhenyao Zhu","submitted_at":"2017-07-24T06:05:21Z","abstract_excerpt":"In this work, we perform an empirical comparison among the CTC, RNN-Transducer, and attention-based Seq2Seq models for end-to-end speech recognition. We show that, without any language model, Seq2Seq and RNN-Transducer models both outperform the best reported CTC models with a language model, on the popular Hub5'00 benchmark. On our internal diverse dataset, these trends continue - RNNTransducer models rescored with a language model after beam search outperform our best CTC models. These results simplify the speech recognition pipeline so that decoding can now be expressed purely as neural net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07413","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":""},"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":"1707.07413","created_at":"2026-05-18T00:39:42.310797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.07413v1","created_at":"2026-05-18T00:39:42.310797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07413","created_at":"2026-05-18T00:39:42.310797+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRSDJOZWMQWP","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRSDJOZWMQWPA3GX","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRSDJOZW","created_at":"2026-05-18T12:31:18.294218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1712.00409","citing_title":"Deep Learning Scaling is Predictable, Empirically","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRSDJOZWMQWPA3GX7GSOXHZFLF","json":"https://pith.science/pith/HRSDJOZWMQWPA3GX7GSOXHZFLF.json","graph_json":"https://pith.science/api/pith-number/HRSDJOZWMQWPA3GX7GSOXHZFLF/graph.json","events_json":"https://pith.science/api/pith-number/HRSDJOZWMQWPA3GX7GSOXHZFLF/events.json","paper":"https://pith.science/paper/HRSDJOZW"},"agent_actions":{"view_html":"https://pith.science/pith/HRSDJOZWMQWPA3GX7GSOXHZFLF","download_json":"https://pith.science/pith/HRSDJOZWMQWPA3GX7GSOXHZFLF.json","view_paper":"https://pith.science/paper/HRSDJOZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.07413&json=true","fetch_graph":"https://pith.science/api/pith-number/HRSDJOZWMQWPA3GX7GSOXHZFLF/graph.json","fetch_events":"https://pith.science/api/pith-number/HRSDJOZWMQWPA3GX7GSOXHZFLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRSDJOZWMQWPA3GX7GSOXHZFLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRSDJOZWMQWPA3GX7GSOXHZFLF/action/storage_attestation","attest_author":"https://pith.science/pith/HRSDJOZWMQWPA3GX7GSOXHZFLF/action/author_attestation","sign_citation":"https://pith.science/pith/HRSDJOZWMQWPA3GX7GSOXHZFLF/action/citation_signature","submit_replication":"https://pith.science/pith/HRSDJOZWMQWPA3GX7GSOXHZFLF/action/replication_record"}},"created_at":"2026-05-18T00:39:42.310797+00:00","updated_at":"2026-05-18T00:39:42.310797+00:00"}