{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BDLQ7RY63IOFXWES3XBKO3SI3F","short_pith_number":"pith:BDLQ7RY6","schema_version":"1.0","canonical_sha256":"08d70fc71eda1c5bd892ddc2a76e48d95e80b0450e6593ef3166616fbd3bcc12","source":{"kind":"arxiv","id":"2406.01205","version":3},"attestation_state":"computed","paper":{"title":"ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hai Huang, Jialong Zuo, Minghui Fang, Qian Chen, Shengpeng Ji, Siqi Zheng, Wen Wang, Xize Cheng, Zehan Wang, Zhou Zhao, Ziyue Jiang","submitted_at":"2024-06-03T11:15:16Z","abstract_excerpt":"In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style. Prior zero-shot TTS models only mimic the speaker's voice without further control and adjustment capabilities while prior controllable TTS models cannot perform speaker-specific voice generation. Therefore, ControlSpeech focuses on a more challenging task: a TTS system with controllable timbre, content, and style at the same time. ControlSpeech takes speech prompts, content prompts, and style prompts as inputs and u"},"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":"2406.01205","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-03T11:15:16Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"54fc39d2fe8be5f4d91c11b650cb3a245cf2ef4a0ff961057af1568499fb72a3","abstract_canon_sha256":"34ecf3621aa01057bb177f9f3568450b57939638fcb1a7e423c8533f13415feb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:37.662230Z","signature_b64":"JpZHJMHQnuvYT0NyAUyrZnc0USf5MDeyp74PazdtoQq+m1A5ILipB5Ma8kEjJSnDNuYo72odp67stCobzMOYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08d70fc71eda1c5bd892ddc2a76e48d95e80b0450e6593ef3166616fbd3bcc12","last_reissued_at":"2026-07-05T11:15:37.661688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:37.661688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hai Huang, Jialong Zuo, Minghui Fang, Qian Chen, Shengpeng Ji, Siqi Zheng, Wen Wang, Xize Cheng, Zehan Wang, Zhou Zhao, Ziyue Jiang","submitted_at":"2024-06-03T11:15:16Z","abstract_excerpt":"In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style. Prior zero-shot TTS models only mimic the speaker's voice without further control and adjustment capabilities while prior controllable TTS models cannot perform speaker-specific voice generation. Therefore, ControlSpeech focuses on a more challenging task: a TTS system with controllable timbre, content, and style at the same time. ControlSpeech takes speech prompts, content prompts, and style prompts as inputs and u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01205","kind":"arxiv","version":3},"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/2406.01205/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":"2406.01205","created_at":"2026-07-05T11:15:37.661763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01205v3","created_at":"2026-07-05T11:15:37.661763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01205","created_at":"2026-07-05T11:15:37.661763+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDLQ7RY63IOF","created_at":"2026-07-05T11:15:37.661763+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDLQ7RY63IOFXWES","created_at":"2026-07-05T11:15:37.661763+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDLQ7RY6","created_at":"2026-07-05T11:15:37.661763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21619","citing_title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDLQ7RY63IOFXWES3XBKO3SI3F","json":"https://pith.science/pith/BDLQ7RY63IOFXWES3XBKO3SI3F.json","graph_json":"https://pith.science/api/pith-number/BDLQ7RY63IOFXWES3XBKO3SI3F/graph.json","events_json":"https://pith.science/api/pith-number/BDLQ7RY63IOFXWES3XBKO3SI3F/events.json","paper":"https://pith.science/paper/BDLQ7RY6"},"agent_actions":{"view_html":"https://pith.science/pith/BDLQ7RY63IOFXWES3XBKO3SI3F","download_json":"https://pith.science/pith/BDLQ7RY63IOFXWES3XBKO3SI3F.json","view_paper":"https://pith.science/paper/BDLQ7RY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01205&json=true","fetch_graph":"https://pith.science/api/pith-number/BDLQ7RY63IOFXWES3XBKO3SI3F/graph.json","fetch_events":"https://pith.science/api/pith-number/BDLQ7RY63IOFXWES3XBKO3SI3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDLQ7RY63IOFXWES3XBKO3SI3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDLQ7RY63IOFXWES3XBKO3SI3F/action/storage_attestation","attest_author":"https://pith.science/pith/BDLQ7RY63IOFXWES3XBKO3SI3F/action/author_attestation","sign_citation":"https://pith.science/pith/BDLQ7RY63IOFXWES3XBKO3SI3F/action/citation_signature","submit_replication":"https://pith.science/pith/BDLQ7RY63IOFXWES3XBKO3SI3F/action/replication_record"}},"created_at":"2026-07-05T11:15:37.661763+00:00","updated_at":"2026-07-05T11:15:37.661763+00:00"}