{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QVFHQB6PZ4SLDL5PYM76FYZ6BY","short_pith_number":"pith:QVFHQB6P","schema_version":"1.0","canonical_sha256":"854a7807cfcf24b1afafc33fe2e33e0e20c8e8724c2c998986d24422c99af6d9","source":{"kind":"arxiv","id":"2106.07699","version":1},"attestation_state":"computed","paper":{"title":"Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrew Slottje, Matthew Snover, Owen Kimball, Shannon Wotherspoon, William Hartmann","submitted_at":"2021-06-14T18:39:18Z","abstract_excerpt":"Modeling code-switched speech is an important problem in automatic speech recognition (ASR). Labeled code-switched data are rare, so monolingual data are often used to model code-switched speech. These monolingual data may be more closely matched to one of the languages in the code-switch pair. We show that such asymmetry can bias prediction toward the better-matched language and degrade overall model performance. To address this issue, we propose a semi-supervised approach for code-switched ASR. We consider the case of English-Mandarin code-switching, and the problem of using monolingual data"},"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":"2106.07699","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-14T18:39:18Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"57c87e11edd523efc06b1eca487996da3b8e539bef9cddb3cea3ab1b3d10d585","abstract_canon_sha256":"aa713d2e2d0f8effee265ad75dcdd1420fc9f537012ef5cf470923c7f74fface"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:32.918451Z","signature_b64":"8pBIw2fP9ZmHMr777YeRRjvymjWP0qPM3wwzwhaWP4V8EW9Zzeo5NuDr2uRXbzBra+aa+kFXQsTte6QpmyvkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854a7807cfcf24b1afafc33fe2e33e0e20c8e8724c2c998986d24422c99af6d9","last_reissued_at":"2026-07-05T02:49:32.918041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:32.918041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using heterogeneity in semi-supervised transcription hypotheses to improve code-switched speech recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Andrew Slottje, Matthew Snover, Owen Kimball, Shannon Wotherspoon, William Hartmann","submitted_at":"2021-06-14T18:39:18Z","abstract_excerpt":"Modeling code-switched speech is an important problem in automatic speech recognition (ASR). Labeled code-switched data are rare, so monolingual data are often used to model code-switched speech. These monolingual data may be more closely matched to one of the languages in the code-switch pair. We show that such asymmetry can bias prediction toward the better-matched language and degrade overall model performance. To address this issue, we propose a semi-supervised approach for code-switched ASR. We consider the case of English-Mandarin code-switching, and the problem of using monolingual data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07699","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/2106.07699/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":"2106.07699","created_at":"2026-07-05T02:49:32.918098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.07699v1","created_at":"2026-07-05T02:49:32.918098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07699","created_at":"2026-07-05T02:49:32.918098+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVFHQB6PZ4SL","created_at":"2026-07-05T02:49:32.918098+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVFHQB6PZ4SLDL5P","created_at":"2026-07-05T02:49:32.918098+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVFHQB6P","created_at":"2026-07-05T02:49:32.918098+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/QVFHQB6PZ4SLDL5PYM76FYZ6BY","json":"https://pith.science/pith/QVFHQB6PZ4SLDL5PYM76FYZ6BY.json","graph_json":"https://pith.science/api/pith-number/QVFHQB6PZ4SLDL5PYM76FYZ6BY/graph.json","events_json":"https://pith.science/api/pith-number/QVFHQB6PZ4SLDL5PYM76FYZ6BY/events.json","paper":"https://pith.science/paper/QVFHQB6P"},"agent_actions":{"view_html":"https://pith.science/pith/QVFHQB6PZ4SLDL5PYM76FYZ6BY","download_json":"https://pith.science/pith/QVFHQB6PZ4SLDL5PYM76FYZ6BY.json","view_paper":"https://pith.science/paper/QVFHQB6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.07699&json=true","fetch_graph":"https://pith.science/api/pith-number/QVFHQB6PZ4SLDL5PYM76FYZ6BY/graph.json","fetch_events":"https://pith.science/api/pith-number/QVFHQB6PZ4SLDL5PYM76FYZ6BY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVFHQB6PZ4SLDL5PYM76FYZ6BY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVFHQB6PZ4SLDL5PYM76FYZ6BY/action/storage_attestation","attest_author":"https://pith.science/pith/QVFHQB6PZ4SLDL5PYM76FYZ6BY/action/author_attestation","sign_citation":"https://pith.science/pith/QVFHQB6PZ4SLDL5PYM76FYZ6BY/action/citation_signature","submit_replication":"https://pith.science/pith/QVFHQB6PZ4SLDL5PYM76FYZ6BY/action/replication_record"}},"created_at":"2026-07-05T02:49:32.918098+00:00","updated_at":"2026-07-05T02:49:32.918098+00:00"}