{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7EBG5LMDXBR6LCAF5J2UIFQ5ON","short_pith_number":"pith:7EBG5LMD","schema_version":"1.0","canonical_sha256":"f9026ead83b863e58805ea7544161d73554b56e28f2055d651f3c44f603870f4","source":{"kind":"arxiv","id":"1908.01060","version":1},"attestation_state":"computed","paper":{"title":"Multilingual Speech Recognition with Corpus Relatedness Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan W. Black, Florian Metze, Siddharth Dalmia, Xinjian Li","submitted_at":"2019-08-02T21:08:13Z","abstract_excerpt":"Multilingual acoustic models have been successfully applied to low-resource speech recognition. Most existing works have combined many small corpora together and pretrained a multilingual model by sampling from each corpus uniformly. The model is eventually fine-tuned on each target corpus. This approach, however, fails to exploit the relatedness and similarity among corpora in the training set. For example, the target corpus might benefit more from a corpus in the same domain or a corpus from a close language. In this work, we propose a simple but useful sampling strategy to take advantage of"},"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":"1908.01060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-02T21:08:13Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9396919bd9b896819e2b7a6cb5b0212f2c473fd26340ef5371e5a549586864b0","abstract_canon_sha256":"69a4cc18ee71ebf664bf7928e9acee73e118d6ace540c829df5640dc2743d545"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:25.988675Z","signature_b64":"QJpELKSa56y53kka9zkk9LcySqmn35r3qbCOYg3HftUyujmn8YwzvRxxuiDytWsQehlZQY2g16FuoYxt4XCzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9026ead83b863e58805ea7544161d73554b56e28f2055d651f3c44f603870f4","last_reissued_at":"2026-07-04T23:51:25.988341Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:25.988341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Speech Recognition with Corpus Relatedness Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alan W. Black, Florian Metze, Siddharth Dalmia, Xinjian Li","submitted_at":"2019-08-02T21:08:13Z","abstract_excerpt":"Multilingual acoustic models have been successfully applied to low-resource speech recognition. Most existing works have combined many small corpora together and pretrained a multilingual model by sampling from each corpus uniformly. The model is eventually fine-tuned on each target corpus. This approach, however, fails to exploit the relatedness and similarity among corpora in the training set. For example, the target corpus might benefit more from a corpus in the same domain or a corpus from a close language. In this work, we propose a simple but useful sampling strategy to take advantage of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01060","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/1908.01060/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":"1908.01060","created_at":"2026-07-04T23:51:25.988395+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01060v1","created_at":"2026-07-04T23:51:25.988395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01060","created_at":"2026-07-04T23:51:25.988395+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EBG5LMDXBR6","created_at":"2026-07-04T23:51:25.988395+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EBG5LMDXBR6LCAF","created_at":"2026-07-04T23:51:25.988395+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EBG5LMD","created_at":"2026-07-04T23:51:25.988395+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/7EBG5LMDXBR6LCAF5J2UIFQ5ON","json":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON.json","graph_json":"https://pith.science/api/pith-number/7EBG5LMDXBR6LCAF5J2UIFQ5ON/graph.json","events_json":"https://pith.science/api/pith-number/7EBG5LMDXBR6LCAF5J2UIFQ5ON/events.json","paper":"https://pith.science/paper/7EBG5LMD"},"agent_actions":{"view_html":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON","download_json":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON.json","view_paper":"https://pith.science/paper/7EBG5LMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01060&json=true","fetch_graph":"https://pith.science/api/pith-number/7EBG5LMDXBR6LCAF5J2UIFQ5ON/graph.json","fetch_events":"https://pith.science/api/pith-number/7EBG5LMDXBR6LCAF5J2UIFQ5ON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/action/storage_attestation","attest_author":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/action/author_attestation","sign_citation":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/action/citation_signature","submit_replication":"https://pith.science/pith/7EBG5LMDXBR6LCAF5J2UIFQ5ON/action/replication_record"}},"created_at":"2026-07-04T23:51:25.988395+00:00","updated_at":"2026-07-04T23:51:25.988395+00:00"}