{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QD3CCE3AG2OQRKFF4FE2AGUGFE","short_pith_number":"pith:QD3CCE3A","schema_version":"1.0","canonical_sha256":"80f6211360369d08a8a5e149a01a8629240c9fe06001ba27161d185eccdcf1c1","source":{"kind":"arxiv","id":"1811.00707","version":1},"attestation_state":"computed","paper":{"title":"Training Neural Speech Recognition Systems with Synthetic Speech Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Jason Li, Ravi Gadde, Vitaly Lavrukhin","submitted_at":"2018-11-02T02:15:46Z","abstract_excerpt":"Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues preventing advancements in ASR research. To address this problem, we propose to augment a natural speech dataset with synthetic speech. We train very large end-to-end neural speech recognition models using the LibriSpeech dataset augmented with synthetic speech. These new models achieve state of the art Word Error Rate (WER) for character-level based models "},"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":"1811.00707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-02T02:15:46Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"14b67761b17842f3565016b4754bfe72efc4cf6d35dea11829e1e625367ae871","abstract_canon_sha256":"a4fe9872807dd69187091ccf5b0962fc74ecd8a75547696aa7bfd9060302a907"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:42.432383Z","signature_b64":"MkPtjVvl9qWo5zQ1jKXVkDah1hN1Vd379uRTzpQ7DLICGt7GRSTzDZJT+EQf5DhX8wLwnluTRqGeGHTntyBdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80f6211360369d08a8a5e149a01a8629240c9fe06001ba27161d185eccdcf1c1","last_reissued_at":"2026-05-18T00:01:42.431825Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:42.431825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Neural Speech Recognition Systems with Synthetic Speech Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Boris Ginsburg, Jason Li, Ravi Gadde, Vitaly Lavrukhin","submitted_at":"2018-11-02T02:15:46Z","abstract_excerpt":"Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues preventing advancements in ASR research. To address this problem, we propose to augment a natural speech dataset with synthetic speech. We train very large end-to-end neural speech recognition models using the LibriSpeech dataset augmented with synthetic speech. These new models achieve state of the art Word Error Rate (WER) for character-level based models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00707","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":"1811.00707","created_at":"2026-05-18T00:01:42.431903+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00707v1","created_at":"2026-05-18T00:01:42.431903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00707","created_at":"2026-05-18T00:01:42.431903+00:00"},{"alias_kind":"pith_short_12","alias_value":"QD3CCE3AG2OQ","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QD3CCE3AG2OQRKFF","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QD3CCE3A","created_at":"2026-05-18T12:32:46.962924+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/QD3CCE3AG2OQRKFF4FE2AGUGFE","json":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE.json","graph_json":"https://pith.science/api/pith-number/QD3CCE3AG2OQRKFF4FE2AGUGFE/graph.json","events_json":"https://pith.science/api/pith-number/QD3CCE3AG2OQRKFF4FE2AGUGFE/events.json","paper":"https://pith.science/paper/QD3CCE3A"},"agent_actions":{"view_html":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE","download_json":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE.json","view_paper":"https://pith.science/paper/QD3CCE3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00707&json=true","fetch_graph":"https://pith.science/api/pith-number/QD3CCE3AG2OQRKFF4FE2AGUGFE/graph.json","fetch_events":"https://pith.science/api/pith-number/QD3CCE3AG2OQRKFF4FE2AGUGFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/action/storage_attestation","attest_author":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/action/author_attestation","sign_citation":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/action/citation_signature","submit_replication":"https://pith.science/pith/QD3CCE3AG2OQRKFF4FE2AGUGFE/action/replication_record"}},"created_at":"2026-05-18T00:01:42.431903+00:00","updated_at":"2026-05-18T00:01:42.431903+00:00"}