{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:I5CUWJMM3X3L23RWEW7A6LYUGZ","short_pith_number":"pith:I5CUWJMM","schema_version":"1.0","canonical_sha256":"47454b258cddf6bd6e3625be0f2f14365e3a2c95b175259c64e81677829056e2","source":{"kind":"arxiv","id":"1811.01690","version":2},"attestation_state":"computed","paper":{"title":"Cycle-consistency training for end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jonathan Le Roux, Ramon Astudillo, Shinji Watanabe, Takaaki Hori, Tomoki Hayashi, Yu Zhang","submitted_at":"2018-11-02T06:32:58Z","abstract_excerpt":"This paper presents a method to train end-to-end automatic speech recognition (ASR) models using unpaired data. Although the end-to-end approach can eliminate the need for expert knowledge such as pronunciation dictionaries to build ASR systems, it still requires a large amount of paired data, i.e., speech utterances and their transcriptions. Cycle-consistency losses have been recently proposed as a way to mitigate the problem of limited paired data. These approaches compose a reverse operation with a given transformation, e.g., text-to-speech (TTS) with ASR, to build a loss that only requires"},"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":"1811.01690","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T06:32:58Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"7b1cfdb01f799f00f682de364475616f885311da12754281bd6d3aabee98730b","abstract_canon_sha256":"a2a697de45ff51b5d6b5ebe9f992eead81f8664d689d5b8c8fb35f7ce320352d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:20.559069Z","signature_b64":"Z3nc9ex/QNSRkbay6CmLLLtk0YXIBKZhwW+rTMGV7r4husMK2RyCO4/8kNYKxvzb2eRp0eKvKTWQ/qx9l2zeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47454b258cddf6bd6e3625be0f2f14365e3a2c95b175259c64e81677829056e2","last_reissued_at":"2026-05-17T23:45:20.558412Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:20.558412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cycle-consistency training for end-to-end speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jonathan Le Roux, Ramon Astudillo, Shinji Watanabe, Takaaki Hori, Tomoki Hayashi, Yu Zhang","submitted_at":"2018-11-02T06:32:58Z","abstract_excerpt":"This paper presents a method to train end-to-end automatic speech recognition (ASR) models using unpaired data. Although the end-to-end approach can eliminate the need for expert knowledge such as pronunciation dictionaries to build ASR systems, it still requires a large amount of paired data, i.e., speech utterances and their transcriptions. Cycle-consistency losses have been recently proposed as a way to mitigate the problem of limited paired data. These approaches compose a reverse operation with a given transformation, e.g., text-to-speech (TTS) with ASR, to build a loss that only requires"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01690","kind":"arxiv","version":2},"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":"1811.01690","created_at":"2026-05-17T23:45:20.558509+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.01690v2","created_at":"2026-05-17T23:45:20.558509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01690","created_at":"2026-05-17T23:45:20.558509+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5CUWJMM3X3L","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5CUWJMM3X3L23RW","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5CUWJMM","created_at":"2026-05-18T12:32:28.185984+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/I5CUWJMM3X3L23RWEW7A6LYUGZ","json":"https://pith.science/pith/I5CUWJMM3X3L23RWEW7A6LYUGZ.json","graph_json":"https://pith.science/api/pith-number/I5CUWJMM3X3L23RWEW7A6LYUGZ/graph.json","events_json":"https://pith.science/api/pith-number/I5CUWJMM3X3L23RWEW7A6LYUGZ/events.json","paper":"https://pith.science/paper/I5CUWJMM"},"agent_actions":{"view_html":"https://pith.science/pith/I5CUWJMM3X3L23RWEW7A6LYUGZ","download_json":"https://pith.science/pith/I5CUWJMM3X3L23RWEW7A6LYUGZ.json","view_paper":"https://pith.science/paper/I5CUWJMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.01690&json=true","fetch_graph":"https://pith.science/api/pith-number/I5CUWJMM3X3L23RWEW7A6LYUGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/I5CUWJMM3X3L23RWEW7A6LYUGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5CUWJMM3X3L23RWEW7A6LYUGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5CUWJMM3X3L23RWEW7A6LYUGZ/action/storage_attestation","attest_author":"https://pith.science/pith/I5CUWJMM3X3L23RWEW7A6LYUGZ/action/author_attestation","sign_citation":"https://pith.science/pith/I5CUWJMM3X3L23RWEW7A6LYUGZ/action/citation_signature","submit_replication":"https://pith.science/pith/I5CUWJMM3X3L23RWEW7A6LYUGZ/action/replication_record"}},"created_at":"2026-05-17T23:45:20.558509+00:00","updated_at":"2026-05-17T23:45:20.558509+00:00"}