{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DU32DY4URJD3E7EA2GBSDJSH6H","short_pith_number":"pith:DU32DY4U","schema_version":"1.0","canonical_sha256":"1d37a1e3948a47b27c80d18321a647f1f3be907d2501b162ac1add43f8646cc1","source":{"kind":"arxiv","id":"2005.07157","version":2},"attestation_state":"computed","paper":{"title":"You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aleksandr Laptev, Aleksey Svischev, Andrei Andrusenko, Ivan Medennikov, Roman Korostik, Sergey Rybin","submitted_at":"2020-05-14T17:24:57Z","abstract_excerpt":"Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing with low-resource tasks. Using recent advances in speech synthesis (text-to-speech, or TTS), we build our TTS system on an ASR training database and then extend the data with synthesized speech to train a recognition model. We argue that, when the training data amount is relatively low, this approach can allow an end-to-end model to reach hybrid systems' quality. For an artificial low-to-medium-resource setup, we co"},"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":"2005.07157","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-14T17:24:57Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"f9493a813a7844e162811441e17aee6989ad02740d74ba8fee66b870bad6b452","abstract_canon_sha256":"e5125ace6b472f065d63dea20bf5f92ca7c733b34da01aadd97dc40274902cb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:30.431385Z","signature_b64":"bSvtbyYyg92cZHCmLjyUr/Ebonxcuc9C9fuGB8uU9T6iFqhiqshamFoPEa7KYjzmZhE6dGjeUm/5Jzise/m9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d37a1e3948a47b27c80d18321a647f1f3be907d2501b162ac1add43f8646cc1","last_reissued_at":"2026-07-05T02:00:30.430958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:30.430958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aleksandr Laptev, Aleksey Svischev, Andrei Andrusenko, Ivan Medennikov, Roman Korostik, Sergey Rybin","submitted_at":"2020-05-14T17:24:57Z","abstract_excerpt":"Data augmentation is one of the most effective ways to make end-to-end automatic speech recognition (ASR) perform close to the conventional hybrid approach, especially when dealing with low-resource tasks. Using recent advances in speech synthesis (text-to-speech, or TTS), we build our TTS system on an ASR training database and then extend the data with synthesized speech to train a recognition model. We argue that, when the training data amount is relatively low, this approach can allow an end-to-end model to reach hybrid systems' quality. For an artificial low-to-medium-resource setup, we co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07157","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.07157/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":"2005.07157","created_at":"2026-07-05T02:00:30.431016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.07157v2","created_at":"2026-07-05T02:00:30.431016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07157","created_at":"2026-07-05T02:00:30.431016+00:00"},{"alias_kind":"pith_short_12","alias_value":"DU32DY4URJD3","created_at":"2026-07-05T02:00:30.431016+00:00"},{"alias_kind":"pith_short_16","alias_value":"DU32DY4URJD3E7EA","created_at":"2026-07-05T02:00:30.431016+00:00"},{"alias_kind":"pith_short_8","alias_value":"DU32DY4U","created_at":"2026-07-05T02:00:30.431016+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/DU32DY4URJD3E7EA2GBSDJSH6H","json":"https://pith.science/pith/DU32DY4URJD3E7EA2GBSDJSH6H.json","graph_json":"https://pith.science/api/pith-number/DU32DY4URJD3E7EA2GBSDJSH6H/graph.json","events_json":"https://pith.science/api/pith-number/DU32DY4URJD3E7EA2GBSDJSH6H/events.json","paper":"https://pith.science/paper/DU32DY4U"},"agent_actions":{"view_html":"https://pith.science/pith/DU32DY4URJD3E7EA2GBSDJSH6H","download_json":"https://pith.science/pith/DU32DY4URJD3E7EA2GBSDJSH6H.json","view_paper":"https://pith.science/paper/DU32DY4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.07157&json=true","fetch_graph":"https://pith.science/api/pith-number/DU32DY4URJD3E7EA2GBSDJSH6H/graph.json","fetch_events":"https://pith.science/api/pith-number/DU32DY4URJD3E7EA2GBSDJSH6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DU32DY4URJD3E7EA2GBSDJSH6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DU32DY4URJD3E7EA2GBSDJSH6H/action/storage_attestation","attest_author":"https://pith.science/pith/DU32DY4URJD3E7EA2GBSDJSH6H/action/author_attestation","sign_citation":"https://pith.science/pith/DU32DY4URJD3E7EA2GBSDJSH6H/action/citation_signature","submit_replication":"https://pith.science/pith/DU32DY4URJD3E7EA2GBSDJSH6H/action/replication_record"}},"created_at":"2026-07-05T02:00:30.431016+00:00","updated_at":"2026-07-05T02:00:30.431016+00:00"}