{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HNSHKTK42C7PZCOSDEY6YNCVAA","short_pith_number":"pith:HNSHKTK4","schema_version":"1.0","canonical_sha256":"3b64754d5cd0befc89d21931ec3455003cbd915567ef9c71c62e4c771999089b","source":{"kind":"arxiv","id":"2606.19381","version":1},"attestation_state":"computed","paper":{"title":"Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Eng Siong Chng, Haoyang Li, Hardik B. Sailor, Hexin Liu, Jeremy H. M. Wong, Leibny Paola Garcia-Perera, Shreyas Gopal, Yizhou Peng, Yue Heng Yeo","submitted_at":"2026-06-14T07:56:36Z","abstract_excerpt":"Code-switch (CS) Automatic Speech Recognition (ASR) remains challenging due to limited availability of high quality CS text-speech pairs for training. Although synthetic data augmentation via Text-to-speech (TTS) has been explored, existing CS TTS approaches primarily optimise reconstruction fidelity and do not explicitly enforce language-boundary consistency, thereby limiting their effectiveness for CS ASR augmentation. This paper proposes a code-mixing guided preference-learning framework that steers synthetic speech generation toward improved code-switching fidelity using the Code Mixing In"},"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":"2606.19381","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-14T07:56:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ed22c5867fd06a6e98b47ce158a992fbe2abd60d587e598a2b3f48af6a7b513","abstract_canon_sha256":"06ea4673ae84e058144968b2128c41c29c26e4fa31b2f9315331bcb5a5e1e21f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:23.693260Z","signature_b64":"NdkwY9BwqIUSj4Uhi3ECzEG4nSHi5bJcAJo8xYfb8OaxRRZPMPDdE3+NAKKQXgiGpouBlxe9JC6PNV/Q8ICDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b64754d5cd0befc89d21931ec3455003cbd915567ef9c71c62e4c771999089b","last_reissued_at":"2026-06-19T16:12:23.692905Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:23.692905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Code-Switching ASR with Code-Mixing Guided Synthetic Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Eng Siong Chng, Haoyang Li, Hardik B. Sailor, Hexin Liu, Jeremy H. M. Wong, Leibny Paola Garcia-Perera, Shreyas Gopal, Yizhou Peng, Yue Heng Yeo","submitted_at":"2026-06-14T07:56:36Z","abstract_excerpt":"Code-switch (CS) Automatic Speech Recognition (ASR) remains challenging due to limited availability of high quality CS text-speech pairs for training. Although synthetic data augmentation via Text-to-speech (TTS) has been explored, existing CS TTS approaches primarily optimise reconstruction fidelity and do not explicitly enforce language-boundary consistency, thereby limiting their effectiveness for CS ASR augmentation. This paper proposes a code-mixing guided preference-learning framework that steers synthetic speech generation toward improved code-switching fidelity using the Code Mixing In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19381","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/2606.19381/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":"2606.19381","created_at":"2026-06-19T16:12:23.692966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19381v1","created_at":"2026-06-19T16:12:23.692966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19381","created_at":"2026-06-19T16:12:23.692966+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNSHKTK42C7P","created_at":"2026-06-19T16:12:23.692966+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNSHKTK42C7PZCOS","created_at":"2026-06-19T16:12:23.692966+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNSHKTK4","created_at":"2026-06-19T16:12:23.692966+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/HNSHKTK42C7PZCOSDEY6YNCVAA","json":"https://pith.science/pith/HNSHKTK42C7PZCOSDEY6YNCVAA.json","graph_json":"https://pith.science/api/pith-number/HNSHKTK42C7PZCOSDEY6YNCVAA/graph.json","events_json":"https://pith.science/api/pith-number/HNSHKTK42C7PZCOSDEY6YNCVAA/events.json","paper":"https://pith.science/paper/HNSHKTK4"},"agent_actions":{"view_html":"https://pith.science/pith/HNSHKTK42C7PZCOSDEY6YNCVAA","download_json":"https://pith.science/pith/HNSHKTK42C7PZCOSDEY6YNCVAA.json","view_paper":"https://pith.science/paper/HNSHKTK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19381&json=true","fetch_graph":"https://pith.science/api/pith-number/HNSHKTK42C7PZCOSDEY6YNCVAA/graph.json","fetch_events":"https://pith.science/api/pith-number/HNSHKTK42C7PZCOSDEY6YNCVAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNSHKTK42C7PZCOSDEY6YNCVAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNSHKTK42C7PZCOSDEY6YNCVAA/action/storage_attestation","attest_author":"https://pith.science/pith/HNSHKTK42C7PZCOSDEY6YNCVAA/action/author_attestation","sign_citation":"https://pith.science/pith/HNSHKTK42C7PZCOSDEY6YNCVAA/action/citation_signature","submit_replication":"https://pith.science/pith/HNSHKTK42C7PZCOSDEY6YNCVAA/action/replication_record"}},"created_at":"2026-06-19T16:12:23.692966+00:00","updated_at":"2026-06-19T16:12:23.692966+00:00"}