{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KXGIQUK7CPV5WC2BOVYXYOODPO","short_pith_number":"pith:KXGIQUK7","schema_version":"1.0","canonical_sha256":"55cc88515f13ebdb0b4175717c39c37ba62dc89d39ea03034a3e3326b6dd8f7f","source":{"kind":"arxiv","id":"2506.14190","version":1},"attestation_state":"computed","paper":{"title":"AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Huy-Dat Tran, Tuan Nguyen","submitted_at":"2025-06-17T05:05:09Z","abstract_excerpt":"Developing code-switched ASR systems is challenging due to language ambiguity and limited exposure to multilingual, code-switched data, while collecting such speech is costly. Prior work generates synthetic audio from text, but these methods are computationally intensive and hard to scale. We introduce AsyncSwitch, a novel asynchronous adaptation framework that leverages large-scale, text-rich web data to pre-expose ASR models to diverse code-switched domains before fine-tuning on paired speech-text corpora. Our three-stage process (1) trains decoder self-attention and feedforward layers on co"},"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":"2506.14190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-17T05:05:09Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"2303a74a29f2c4991049766360bf4162ed6b7214873f59fe9fd14600880d3bcd","abstract_canon_sha256":"bf0fdbb8fbd20a31730975a539eb9fc057066218c5f8bc217a3c5807275e7d05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:50.505379Z","signature_b64":"6kpWd4WUC4MAS9ITJVHH4NiyHoNt0Sx3dsEMBFFiejRC2OYcPtkaaDyRLd1E0i5C6PBqeeQjT6nfHzPtbJV5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55cc88515f13ebdb0b4175717c39c37ba62dc89d39ea03034a3e3326b6dd8f7f","last_reissued_at":"2026-07-05T11:22:50.504878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:50.504878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AsyncSwitch: Asynchronous Text-Speech Adaptation for Code-Switched ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Huy-Dat Tran, Tuan Nguyen","submitted_at":"2025-06-17T05:05:09Z","abstract_excerpt":"Developing code-switched ASR systems is challenging due to language ambiguity and limited exposure to multilingual, code-switched data, while collecting such speech is costly. Prior work generates synthetic audio from text, but these methods are computationally intensive and hard to scale. We introduce AsyncSwitch, a novel asynchronous adaptation framework that leverages large-scale, text-rich web data to pre-expose ASR models to diverse code-switched domains before fine-tuning on paired speech-text corpora. Our three-stage process (1) trains decoder self-attention and feedforward layers on co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14190","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/2506.14190/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":"2506.14190","created_at":"2026-07-05T11:22:50.504937+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14190v1","created_at":"2026-07-05T11:22:50.504937+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14190","created_at":"2026-07-05T11:22:50.504937+00:00"},{"alias_kind":"pith_short_12","alias_value":"KXGIQUK7CPV5","created_at":"2026-07-05T11:22:50.504937+00:00"},{"alias_kind":"pith_short_16","alias_value":"KXGIQUK7CPV5WC2B","created_at":"2026-07-05T11:22:50.504937+00:00"},{"alias_kind":"pith_short_8","alias_value":"KXGIQUK7","created_at":"2026-07-05T11:22:50.504937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05846","citing_title":"Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KXGIQUK7CPV5WC2BOVYXYOODPO","json":"https://pith.science/pith/KXGIQUK7CPV5WC2BOVYXYOODPO.json","graph_json":"https://pith.science/api/pith-number/KXGIQUK7CPV5WC2BOVYXYOODPO/graph.json","events_json":"https://pith.science/api/pith-number/KXGIQUK7CPV5WC2BOVYXYOODPO/events.json","paper":"https://pith.science/paper/KXGIQUK7"},"agent_actions":{"view_html":"https://pith.science/pith/KXGIQUK7CPV5WC2BOVYXYOODPO","download_json":"https://pith.science/pith/KXGIQUK7CPV5WC2BOVYXYOODPO.json","view_paper":"https://pith.science/paper/KXGIQUK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14190&json=true","fetch_graph":"https://pith.science/api/pith-number/KXGIQUK7CPV5WC2BOVYXYOODPO/graph.json","fetch_events":"https://pith.science/api/pith-number/KXGIQUK7CPV5WC2BOVYXYOODPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KXGIQUK7CPV5WC2BOVYXYOODPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KXGIQUK7CPV5WC2BOVYXYOODPO/action/storage_attestation","attest_author":"https://pith.science/pith/KXGIQUK7CPV5WC2BOVYXYOODPO/action/author_attestation","sign_citation":"https://pith.science/pith/KXGIQUK7CPV5WC2BOVYXYOODPO/action/citation_signature","submit_replication":"https://pith.science/pith/KXGIQUK7CPV5WC2BOVYXYOODPO/action/replication_record"}},"created_at":"2026-07-05T11:22:50.504937+00:00","updated_at":"2026-07-05T11:22:50.504937+00:00"}