{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZXC6SZJPR4Q2ITZOT5CCSPSFBG","short_pith_number":"pith:ZXC6SZJP","schema_version":"1.0","canonical_sha256":"cdc5e9652f8f21a44f2e9f44293e4509aa57445b3b733ae9ca1dcd082124d36a","source":{"kind":"arxiv","id":"2608.08362","version":1},"attestation_state":"computed","paper":{"title":"CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.SD"],"primary_cat":"eess.AS","authors_text":"Caren Chen, David Harwath, Gerard Medioni, Manoj Aggarwal, Rohith Kumar, Xiaohang Sun, Zhisheng Zheng, Zhu Liu","submitted_at":"2026-08-08T23:17:09Z","abstract_excerpt":"Recent Text-To-Speech (TTS) systems have achieved strong naturalness and zero-shot voice cloning performance, but fine-grained control of expressive speech at the word or phoneme level remains challenging. We propose CtrlSpeech, a controllable, expressive TTS framework with coarse-to-fine control. Built on the DiTAR architecture, CtrlSpeech combines global speaker conditioning with phone-aligned pitch, loudness, and duration signals, enabling localized prosodic control while preserving the target speaker's timbre. This design allows users to adjust expressive attributes at a fine temporal gran"},"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":"2608.08362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-08-08T23:17:09Z","cross_cats_sorted":["cs.HC","cs.SD"],"title_canon_sha256":"1b80c716731f9b6e11d127125215e4df6b58d1d8821ee191f52d3dfdbc88ae9e","abstract_canon_sha256":"5642db96c8afc7dfd51cf5e24a86eeee0b35c7917bd7895c75e5bf1563eb300b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:25.432609Z","signature_b64":"EzGl0FoRzzEKNr9HJ9qWK07d+VGHDlbgCgYSp80fZZ7WajB1XCTviKYaZ4hR9US6hgbtXdBH9AnxzNtwwGIlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdc5e9652f8f21a44f2e9f44293e4509aa57445b3b733ae9ca1dcd082124d36a","last_reissued_at":"2026-08-11T01:22:25.430170Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:25.430170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.SD"],"primary_cat":"eess.AS","authors_text":"Caren Chen, David Harwath, Gerard Medioni, Manoj Aggarwal, Rohith Kumar, Xiaohang Sun, Zhisheng Zheng, Zhu Liu","submitted_at":"2026-08-08T23:17:09Z","abstract_excerpt":"Recent Text-To-Speech (TTS) systems have achieved strong naturalness and zero-shot voice cloning performance, but fine-grained control of expressive speech at the word or phoneme level remains challenging. We propose CtrlSpeech, a controllable, expressive TTS framework with coarse-to-fine control. Built on the DiTAR architecture, CtrlSpeech combines global speaker conditioning with phone-aligned pitch, loudness, and duration signals, enabling localized prosodic control while preserving the target speaker's timbre. This design allows users to adjust expressive attributes at a fine temporal gran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08362","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/2608.08362/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":"2608.08362","created_at":"2026-08-11T01:22:25.430921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.08362v1","created_at":"2026-08-11T01:22:25.430921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08362","created_at":"2026-08-11T01:22:25.430921+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXC6SZJPR4Q2","created_at":"2026-08-11T01:22:25.430921+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXC6SZJPR4Q2ITZO","created_at":"2026-08-11T01:22:25.430921+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXC6SZJP","created_at":"2026-08-11T01:22:25.430921+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.08362","citing_title":"CtrlSpeech: Coarse-to-Fine Control for Expressive Speech Synthesis","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXC6SZJPR4Q2ITZOT5CCSPSFBG","json":"https://pith.science/pith/ZXC6SZJPR4Q2ITZOT5CCSPSFBG.json","graph_json":"https://pith.science/api/pith-number/ZXC6SZJPR4Q2ITZOT5CCSPSFBG/graph.json","events_json":"https://pith.science/api/pith-number/ZXC6SZJPR4Q2ITZOT5CCSPSFBG/events.json","paper":"https://pith.science/paper/ZXC6SZJP"},"agent_actions":{"view_html":"https://pith.science/pith/ZXC6SZJPR4Q2ITZOT5CCSPSFBG","download_json":"https://pith.science/pith/ZXC6SZJPR4Q2ITZOT5CCSPSFBG.json","view_paper":"https://pith.science/paper/ZXC6SZJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.08362&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXC6SZJPR4Q2ITZOT5CCSPSFBG/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXC6SZJPR4Q2ITZOT5CCSPSFBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXC6SZJPR4Q2ITZOT5CCSPSFBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXC6SZJPR4Q2ITZOT5CCSPSFBG/action/storage_attestation","attest_author":"https://pith.science/pith/ZXC6SZJPR4Q2ITZOT5CCSPSFBG/action/author_attestation","sign_citation":"https://pith.science/pith/ZXC6SZJPR4Q2ITZOT5CCSPSFBG/action/citation_signature","submit_replication":"https://pith.science/pith/ZXC6SZJPR4Q2ITZOT5CCSPSFBG/action/replication_record"}},"created_at":"2026-08-11T01:22:25.430921+00:00","updated_at":"2026-08-11T01:22:25.430921+00:00"}