{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KB6MU7LDQS263PBRJ2ZINNULHP","short_pith_number":"pith:KB6MU7LD","schema_version":"1.0","canonical_sha256":"507cca7d6384b5edbc314eb286b68b3bfefe006961516bf7caa197339f882f23","source":{"kind":"arxiv","id":"2407.17852","version":1},"attestation_state":"computed","paper":{"title":"Scaling A Simple Approach to Zero-Shot Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinming Zhao, Michael Auli, Vineel Pratap","submitted_at":"2024-07-25T08:08:55Z","abstract_excerpt":"Despite rapid progress in increasing the language coverage of automatic speech recognition, the field is still far from covering all languages with a known writing script. Recent work showed promising results with a zero-shot approach requiring only a small amount of text data, however, accuracy heavily depends on the quality of the used phonemizer which is often weak for unseen languages. In this paper, we present MMS Zero-shot a conceptually simpler approach based on romanization and an acoustic model trained on data in 1,078 different languages or three orders of magnitude more than prior a"},"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":"2407.17852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-25T08:08:55Z","cross_cats_sorted":[],"title_canon_sha256":"fcea9f05a9c3e497779c52a642ee6ab3b07df0b85ce6ec2eee2a6e1341559e77","abstract_canon_sha256":"fd8e482ab74f70871a408f5d31d955780c6cdd3f808dd08f22955484af53759f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:22.562327Z","signature_b64":"oEB/Cnjb92tBYViOexC3kI4Vo36qLfB0l06RgfxWrn2KFFnWdxuojsVU/bfKf1oMzDbOm3/qiWwSaFSQfXo1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"507cca7d6384b5edbc314eb286b68b3bfefe006961516bf7caa197339f882f23","last_reissued_at":"2026-07-05T08:48:22.561905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:22.561905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling A Simple Approach to Zero-Shot Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinming Zhao, Michael Auli, Vineel Pratap","submitted_at":"2024-07-25T08:08:55Z","abstract_excerpt":"Despite rapid progress in increasing the language coverage of automatic speech recognition, the field is still far from covering all languages with a known writing script. Recent work showed promising results with a zero-shot approach requiring only a small amount of text data, however, accuracy heavily depends on the quality of the used phonemizer which is often weak for unseen languages. In this paper, we present MMS Zero-shot a conceptually simpler approach based on romanization and an acoustic model trained on data in 1,078 different languages or three orders of magnitude more than prior a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17852","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/2407.17852/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":"2407.17852","created_at":"2026-07-05T08:48:22.561961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17852v1","created_at":"2026-07-05T08:48:22.561961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17852","created_at":"2026-07-05T08:48:22.561961+00:00"},{"alias_kind":"pith_short_12","alias_value":"KB6MU7LDQS26","created_at":"2026-07-05T08:48:22.561961+00:00"},{"alias_kind":"pith_short_16","alias_value":"KB6MU7LDQS263PBR","created_at":"2026-07-05T08:48:22.561961+00:00"},{"alias_kind":"pith_short_8","alias_value":"KB6MU7LD","created_at":"2026-07-05T08:48:22.561961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24561","citing_title":"Improving Language and Modality Transfer in Translation by Character-level Modeling","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP","json":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP.json","graph_json":"https://pith.science/api/pith-number/KB6MU7LDQS263PBRJ2ZINNULHP/graph.json","events_json":"https://pith.science/api/pith-number/KB6MU7LDQS263PBRJ2ZINNULHP/events.json","paper":"https://pith.science/paper/KB6MU7LD"},"agent_actions":{"view_html":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP","download_json":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP.json","view_paper":"https://pith.science/paper/KB6MU7LD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17852&json=true","fetch_graph":"https://pith.science/api/pith-number/KB6MU7LDQS263PBRJ2ZINNULHP/graph.json","fetch_events":"https://pith.science/api/pith-number/KB6MU7LDQS263PBRJ2ZINNULHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP/action/storage_attestation","attest_author":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP/action/author_attestation","sign_citation":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP/action/citation_signature","submit_replication":"https://pith.science/pith/KB6MU7LDQS263PBRJ2ZINNULHP/action/replication_record"}},"created_at":"2026-07-05T08:48:22.561961+00:00","updated_at":"2026-07-05T08:48:22.561961+00:00"}