{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QXSOPAORAXLAG6KTPMD2XHYLMI","short_pith_number":"pith:QXSOPAOR","schema_version":"1.0","canonical_sha256":"85e4e781d105d60379537b07ab9f0b621330cc28d19232700ebf9d36e34fcc82","source":{"kind":"arxiv","id":"2210.14567","version":1},"attestation_state":"computed","paper":{"title":"Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Andy W. H. Khong, Haihua Xu, Hexin Liu, Leibny Paola Garcia, Sanjeev Khudanpur, Yi He","submitted_at":"2022-10-26T08:55:25Z","abstract_excerpt":"Code-switching (CS) refers to the phenomenon that languages switch within a speech signal and leads to language confusion for automatic speech recognition (ASR). This paper aims to address language confusion for improving CS-ASR from two perspectives: incorporating and disentangling language information. We incorporate language information in the CS-ASR model by dynamically biasing the model with token-level language posteriors which are outputs of a sequence-to-sequence auxiliary language diarization module. In contrast, the disentangling process reduces the difference between languages via 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":"2210.14567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-10-26T08:55:25Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0c7d83ea81bc9d05e9639426f0360f0c44111ce93dff45128c90109f0bba0adf","abstract_canon_sha256":"0ed17f557920a9f688a18f901d4834344a16b569ec96947252604681c641cf8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:46.943410Z","signature_b64":"sTz633lHM6ztSbnSDwvXalgMyEZAB4FuGFTQKoisxCR/LfglRqGsDgLu4RM0V20+RRfXUhnyc7rDXyA0PFksDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85e4e781d105d60379537b07ab9f0b621330cc28d19232700ebf9d36e34fcc82","last_reissued_at":"2026-07-05T05:10:46.942935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:46.942935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reducing Language confusion for Code-switching Speech Recognition with Token-level Language Diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Andy W. H. Khong, Haihua Xu, Hexin Liu, Leibny Paola Garcia, Sanjeev Khudanpur, Yi He","submitted_at":"2022-10-26T08:55:25Z","abstract_excerpt":"Code-switching (CS) refers to the phenomenon that languages switch within a speech signal and leads to language confusion for automatic speech recognition (ASR). This paper aims to address language confusion for improving CS-ASR from two perspectives: incorporating and disentangling language information. We incorporate language information in the CS-ASR model by dynamically biasing the model with token-level language posteriors which are outputs of a sequence-to-sequence auxiliary language diarization module. In contrast, the disentangling process reduces the difference between languages via a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14567","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/2210.14567/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":"2210.14567","created_at":"2026-07-05T05:10:46.942994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14567v1","created_at":"2026-07-05T05:10:46.942994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14567","created_at":"2026-07-05T05:10:46.942994+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXSOPAORAXLA","created_at":"2026-07-05T05:10:46.942994+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXSOPAORAXLAG6KT","created_at":"2026-07-05T05:10:46.942994+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXSOPAOR","created_at":"2026-07-05T05:10:46.942994+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/QXSOPAORAXLAG6KTPMD2XHYLMI","json":"https://pith.science/pith/QXSOPAORAXLAG6KTPMD2XHYLMI.json","graph_json":"https://pith.science/api/pith-number/QXSOPAORAXLAG6KTPMD2XHYLMI/graph.json","events_json":"https://pith.science/api/pith-number/QXSOPAORAXLAG6KTPMD2XHYLMI/events.json","paper":"https://pith.science/paper/QXSOPAOR"},"agent_actions":{"view_html":"https://pith.science/pith/QXSOPAORAXLAG6KTPMD2XHYLMI","download_json":"https://pith.science/pith/QXSOPAORAXLAG6KTPMD2XHYLMI.json","view_paper":"https://pith.science/paper/QXSOPAOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14567&json=true","fetch_graph":"https://pith.science/api/pith-number/QXSOPAORAXLAG6KTPMD2XHYLMI/graph.json","fetch_events":"https://pith.science/api/pith-number/QXSOPAORAXLAG6KTPMD2XHYLMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXSOPAORAXLAG6KTPMD2XHYLMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXSOPAORAXLAG6KTPMD2XHYLMI/action/storage_attestation","attest_author":"https://pith.science/pith/QXSOPAORAXLAG6KTPMD2XHYLMI/action/author_attestation","sign_citation":"https://pith.science/pith/QXSOPAORAXLAG6KTPMD2XHYLMI/action/citation_signature","submit_replication":"https://pith.science/pith/QXSOPAORAXLAG6KTPMD2XHYLMI/action/replication_record"}},"created_at":"2026-07-05T05:10:46.942994+00:00","updated_at":"2026-07-05T05:10:46.942994+00:00"}