{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VFKTGZP335III24SKFLSH4JROY","short_pith_number":"pith:VFKTGZP3","schema_version":"1.0","canonical_sha256":"a9553365fbdf50846b92515723f13176330f523192e543ba20b7b0d91a166f98","source":{"kind":"arxiv","id":"2505.16972","version":1},"attestation_state":"computed","paper":{"title":"From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Lu Xu, Shanbo Cheng, Tianduo Wang, Wei Lu","submitted_at":"2025-05-22T17:51:05Z","abstract_excerpt":"Recent advances in Automatic Speech Recognition (ASR) have been largely fueled by massive speech corpora. However, extending coverage to diverse languages with limited resources remains a formidable challenge. This paper introduces Speech Back-Translation, a scalable pipeline that improves multilingual ASR models by converting large-scale text corpora into synthetic speech via off-the-shelf text-to-speech (TTS) models. We demonstrate that just tens of hours of real transcribed speech can effectively train TTS models to generate synthetic speech at hundreds of times the original volume while ma"},"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":"2505.16972","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T17:51:05Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"96ffba97e27bf6229512215edfec2683b0eb6ea7e14c17fe3c43c904cbf07704","abstract_canon_sha256":"bee8056317571642d7d26670eb5d79f8334fece9fdbd9770971127b816a1fddf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:43.938487Z","signature_b64":"GpDkOcSMQIcQB6eHMSeCaWixnHsOu9mbUlvJDja0SoTYrM9cWWiEpQJZT92VkX68og0PbYYEcOgiTxYpbzg4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9553365fbdf50846b92515723f13176330f523192e543ba20b7b0d91a166f98","last_reissued_at":"2026-07-05T11:07:43.937890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:43.937890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Lu Xu, Shanbo Cheng, Tianduo Wang, Wei Lu","submitted_at":"2025-05-22T17:51:05Z","abstract_excerpt":"Recent advances in Automatic Speech Recognition (ASR) have been largely fueled by massive speech corpora. However, extending coverage to diverse languages with limited resources remains a formidable challenge. This paper introduces Speech Back-Translation, a scalable pipeline that improves multilingual ASR models by converting large-scale text corpora into synthetic speech via off-the-shelf text-to-speech (TTS) models. We demonstrate that just tens of hours of real transcribed speech can effectively train TTS models to generate synthetic speech at hundreds of times the original volume while ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16972","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/2505.16972/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":"2505.16972","created_at":"2026-07-05T11:07:43.937961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16972v1","created_at":"2026-07-05T11:07:43.937961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16972","created_at":"2026-07-05T11:07:43.937961+00:00"},{"alias_kind":"pith_short_12","alias_value":"VFKTGZP335II","created_at":"2026-07-05T11:07:43.937961+00:00"},{"alias_kind":"pith_short_16","alias_value":"VFKTGZP335III24S","created_at":"2026-07-05T11:07:43.937961+00:00"},{"alias_kind":"pith_short_8","alias_value":"VFKTGZP3","created_at":"2026-07-05T11:07:43.937961+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/VFKTGZP335III24SKFLSH4JROY","json":"https://pith.science/pith/VFKTGZP335III24SKFLSH4JROY.json","graph_json":"https://pith.science/api/pith-number/VFKTGZP335III24SKFLSH4JROY/graph.json","events_json":"https://pith.science/api/pith-number/VFKTGZP335III24SKFLSH4JROY/events.json","paper":"https://pith.science/paper/VFKTGZP3"},"agent_actions":{"view_html":"https://pith.science/pith/VFKTGZP335III24SKFLSH4JROY","download_json":"https://pith.science/pith/VFKTGZP335III24SKFLSH4JROY.json","view_paper":"https://pith.science/paper/VFKTGZP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16972&json=true","fetch_graph":"https://pith.science/api/pith-number/VFKTGZP335III24SKFLSH4JROY/graph.json","fetch_events":"https://pith.science/api/pith-number/VFKTGZP335III24SKFLSH4JROY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VFKTGZP335III24SKFLSH4JROY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VFKTGZP335III24SKFLSH4JROY/action/storage_attestation","attest_author":"https://pith.science/pith/VFKTGZP335III24SKFLSH4JROY/action/author_attestation","sign_citation":"https://pith.science/pith/VFKTGZP335III24SKFLSH4JROY/action/citation_signature","submit_replication":"https://pith.science/pith/VFKTGZP335III24SKFLSH4JROY/action/replication_record"}},"created_at":"2026-07-05T11:07:43.937961+00:00","updated_at":"2026-07-05T11:07:43.937961+00:00"}