{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HA542PIAPRNA2ARMVDRS3NQKH7","short_pith_number":"pith:HA542PIA","schema_version":"1.0","canonical_sha256":"383bcd3d007c5a0d022ca8e32db60a3fce55967ba991ab8b082b6b73d32ecde7","source":{"kind":"arxiv","id":"2409.10429","version":2},"attestation_state":"computed","paper":{"title":"SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hung-yi Lee, Ming-Hao Hsu","submitted_at":"2024-09-16T16:04:16Z","abstract_excerpt":"Automatic Speech Recognition (ASR) models demonstrate outstanding performance on high-resource languages but face significant challenges when applied to low-resource languages due to limited training data and insufficient cross-lingual generalization. Existing adaptation strategies, such as shallow fusion, data augmentation, and direct fine-tuning, either rely on external resources, suffer computational inefficiencies, or fail in test-time adaptation scenarios. To address these limitations, we introduce Speech Meta In-Context LEarning (SMILE), an innovative framework that combines meta-learnin"},"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":"2409.10429","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T16:04:16Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"00ec75acdfbbd71c2844ef479470dfd7f5df5ec5f3e1e005a691b5c9ccd5643e","abstract_canon_sha256":"308d7f6743ce3660f1dfcca1f6af1c307dcc7f25f15c53a52ed04d3ea7cc7a14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:35.833802Z","signature_b64":"gEdkcHuHqf+soUteVhSYVSUsJy4APIhL7iYeaG83wx4/fdJKIFVkMeH1XD2heeX3B8jRPwfy0yx6wJyC7vETBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"383bcd3d007c5a0d022ca8e32db60a3fce55967ba991ab8b082b6b73d32ecde7","last_reissued_at":"2026-07-05T11:21:35.833238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:35.833238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hung-yi Lee, Ming-Hao Hsu","submitted_at":"2024-09-16T16:04:16Z","abstract_excerpt":"Automatic Speech Recognition (ASR) models demonstrate outstanding performance on high-resource languages but face significant challenges when applied to low-resource languages due to limited training data and insufficient cross-lingual generalization. Existing adaptation strategies, such as shallow fusion, data augmentation, and direct fine-tuning, either rely on external resources, suffer computational inefficiencies, or fail in test-time adaptation scenarios. To address these limitations, we introduce Speech Meta In-Context LEarning (SMILE), an innovative framework that combines meta-learnin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10429","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/2409.10429/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":"2409.10429","created_at":"2026-07-05T11:21:35.833300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10429v2","created_at":"2026-07-05T11:21:35.833300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10429","created_at":"2026-07-05T11:21:35.833300+00:00"},{"alias_kind":"pith_short_12","alias_value":"HA542PIAPRNA","created_at":"2026-07-05T11:21:35.833300+00:00"},{"alias_kind":"pith_short_16","alias_value":"HA542PIAPRNA2ARM","created_at":"2026-07-05T11:21:35.833300+00:00"},{"alias_kind":"pith_short_8","alias_value":"HA542PIA","created_at":"2026-07-05T11:21:35.833300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19157","citing_title":"IndicContextEval: A Benchmark for Evaluating Context Utilisation in Audio Large Language Models Across 8 Indic Languages","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02615","citing_title":"FSA-GRPO: Teaching Auditory LLMs to Use Few-shot Demonstrations","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HA542PIAPRNA2ARMVDRS3NQKH7","json":"https://pith.science/pith/HA542PIAPRNA2ARMVDRS3NQKH7.json","graph_json":"https://pith.science/api/pith-number/HA542PIAPRNA2ARMVDRS3NQKH7/graph.json","events_json":"https://pith.science/api/pith-number/HA542PIAPRNA2ARMVDRS3NQKH7/events.json","paper":"https://pith.science/paper/HA542PIA"},"agent_actions":{"view_html":"https://pith.science/pith/HA542PIAPRNA2ARMVDRS3NQKH7","download_json":"https://pith.science/pith/HA542PIAPRNA2ARMVDRS3NQKH7.json","view_paper":"https://pith.science/paper/HA542PIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10429&json=true","fetch_graph":"https://pith.science/api/pith-number/HA542PIAPRNA2ARMVDRS3NQKH7/graph.json","fetch_events":"https://pith.science/api/pith-number/HA542PIAPRNA2ARMVDRS3NQKH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HA542PIAPRNA2ARMVDRS3NQKH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HA542PIAPRNA2ARMVDRS3NQKH7/action/storage_attestation","attest_author":"https://pith.science/pith/HA542PIAPRNA2ARMVDRS3NQKH7/action/author_attestation","sign_citation":"https://pith.science/pith/HA542PIAPRNA2ARMVDRS3NQKH7/action/citation_signature","submit_replication":"https://pith.science/pith/HA542PIAPRNA2ARMVDRS3NQKH7/action/replication_record"}},"created_at":"2026-07-05T11:21:35.833300+00:00","updated_at":"2026-07-05T11:21:35.833300+00:00"}