{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3AV7B5P6442GZ2KSGJLQLUT7UE","short_pith_number":"pith:3AV7B5P6","schema_version":"1.0","canonical_sha256":"d82bf0f5fee7346ce952325705d27fa11983ee7c1525269e46bfc0868101ce8f","source":{"kind":"arxiv","id":"2606.01677","version":1},"attestation_state":"computed","paper":{"title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Qian Chen, Wen Wang, Xiangang Li, Yang Ai, Yufei Shi, Zhen-Hua Ling","submitted_at":"2026-06-01T04:35:28Z","abstract_excerpt":"We propose UniVocal, a unified framework that implicitly infers vocal modes from text context to pioneer Speech-Singing Code-Switching (SCS) Synthesis - a task where transitions are autonomously driven by textual semantics, akin to seamless human language blending. Unlike single-mode generation or systems relying on switching-control tags, our proposed UniVocal implicitly infers vocal modes solely from text context. To achieve this, we employ a data-efficient two-stage curriculum learning strategy that progressively trains a competitive TTS system to acquire the desired SCS capability. Address"},"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":"2606.01677","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-01T04:35:28Z","cross_cats_sorted":[],"title_canon_sha256":"b7aa182df2c857005f70c30f4c700e63d69b0a569a7c604db3f950bda0e914a5","abstract_canon_sha256":"0e71e3ae52dc6390a20d133f9ddf1a70d21c9ce9558937c4b374f0b355c96ad1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:39.881062Z","signature_b64":"3qiUdH93F9S2Rj2bmfalDnc9G6jSPJnP3mLOdquJA2q2ESfRugX/CpHX/1L4FIwIJZvBKKepU65p8ydmiqUfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d82bf0f5fee7346ce952325705d27fa11983ee7c1525269e46bfc0868101ce8f","last_reissued_at":"2026-06-02T02:04:39.880679Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:39.880679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Qian Chen, Wen Wang, Xiangang Li, Yang Ai, Yufei Shi, Zhen-Hua Ling","submitted_at":"2026-06-01T04:35:28Z","abstract_excerpt":"We propose UniVocal, a unified framework that implicitly infers vocal modes from text context to pioneer Speech-Singing Code-Switching (SCS) Synthesis - a task where transitions are autonomously driven by textual semantics, akin to seamless human language blending. Unlike single-mode generation or systems relying on switching-control tags, our proposed UniVocal implicitly infers vocal modes solely from text context. To achieve this, we employ a data-efficient two-stage curriculum learning strategy that progressively trains a competitive TTS system to acquire the desired SCS capability. Address"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01677","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/2606.01677/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":"2606.01677","created_at":"2026-06-02T02:04:39.880734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01677v1","created_at":"2026-06-02T02:04:39.880734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01677","created_at":"2026-06-02T02:04:39.880734+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AV7B5P6442G","created_at":"2026-06-02T02:04:39.880734+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AV7B5P6442GZ2KS","created_at":"2026-06-02T02:04:39.880734+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AV7B5P6","created_at":"2026-06-02T02:04:39.880734+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/3AV7B5P6442GZ2KSGJLQLUT7UE","json":"https://pith.science/pith/3AV7B5P6442GZ2KSGJLQLUT7UE.json","graph_json":"https://pith.science/api/pith-number/3AV7B5P6442GZ2KSGJLQLUT7UE/graph.json","events_json":"https://pith.science/api/pith-number/3AV7B5P6442GZ2KSGJLQLUT7UE/events.json","paper":"https://pith.science/paper/3AV7B5P6"},"agent_actions":{"view_html":"https://pith.science/pith/3AV7B5P6442GZ2KSGJLQLUT7UE","download_json":"https://pith.science/pith/3AV7B5P6442GZ2KSGJLQLUT7UE.json","view_paper":"https://pith.science/paper/3AV7B5P6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01677&json=true","fetch_graph":"https://pith.science/api/pith-number/3AV7B5P6442GZ2KSGJLQLUT7UE/graph.json","fetch_events":"https://pith.science/api/pith-number/3AV7B5P6442GZ2KSGJLQLUT7UE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AV7B5P6442GZ2KSGJLQLUT7UE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AV7B5P6442GZ2KSGJLQLUT7UE/action/storage_attestation","attest_author":"https://pith.science/pith/3AV7B5P6442GZ2KSGJLQLUT7UE/action/author_attestation","sign_citation":"https://pith.science/pith/3AV7B5P6442GZ2KSGJLQLUT7UE/action/citation_signature","submit_replication":"https://pith.science/pith/3AV7B5P6442GZ2KSGJLQLUT7UE/action/replication_record"}},"created_at":"2026-06-02T02:04:39.880734+00:00","updated_at":"2026-06-02T02:04:39.880734+00:00"}