{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HTJU254KVK7X2VE4N5CIS6SXXS","short_pith_number":"pith:HTJU254K","schema_version":"1.0","canonical_sha256":"3cd34d778aaabf7d549c6f44897a57bc99d062c9c58bc5691b8da965102ef017","source":{"kind":"arxiv","id":"2406.16314","version":1},"attestation_state":"computed","paper":{"title":"DreamVoice: Text-Guided Voice Conversion","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Helin Wang, Jiarui Hai, Karan Thakkar, Mounya Elhilali, Zengyi Qin","submitted_at":"2024-06-24T04:46:50Z","abstract_excerpt":"Generative voice technologies are rapidly evolving, offering opportunities for more personalized and inclusive experiences. Traditional one-shot voice conversion (VC) requires a target recording during inference, limiting ease of usage in generating desired voice timbres. Text-guided generation offers an intuitive solution to convert voices to desired \"DreamVoices\" according to the users' needs. Our paper presents two major contributions to VC technology: (1) DreamVoiceDB, a robust dataset of voice timbre annotations for 900 speakers from VCTK and LibriTTS. (2) Two text-guided VC methods: Drea"},"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":"2406.16314","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-24T04:46:50Z","cross_cats_sorted":[],"title_canon_sha256":"94bffeafbf0643c0c2b363053db3a90a6bafd32e54b22511c1f8ffb841747b42","abstract_canon_sha256":"70955dfaa06037e410dc243991133c0ddfc408e8373f2db3ab2407307c1d0997"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:56.551926Z","signature_b64":"G93gLmkEqwihEzlRSr8zbLMVXRQWWu9ZU96Hbn60LSeZEo0AgH3fgZGCzQMqo5UQ7sUa/775vj7y8dBMyjgGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cd34d778aaabf7d549c6f44897a57bc99d062c9c58bc5691b8da965102ef017","last_reissued_at":"2026-07-05T08:35:56.551535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:56.551535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamVoice: Text-Guided Voice Conversion","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Helin Wang, Jiarui Hai, Karan Thakkar, Mounya Elhilali, Zengyi Qin","submitted_at":"2024-06-24T04:46:50Z","abstract_excerpt":"Generative voice technologies are rapidly evolving, offering opportunities for more personalized and inclusive experiences. Traditional one-shot voice conversion (VC) requires a target recording during inference, limiting ease of usage in generating desired voice timbres. Text-guided generation offers an intuitive solution to convert voices to desired \"DreamVoices\" according to the users' needs. Our paper presents two major contributions to VC technology: (1) DreamVoiceDB, a robust dataset of voice timbre annotations for 900 speakers from VCTK and LibriTTS. (2) Two text-guided VC methods: Drea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16314","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/2406.16314/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":"2406.16314","created_at":"2026-07-05T08:35:56.551592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16314v1","created_at":"2026-07-05T08:35:56.551592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16314","created_at":"2026-07-05T08:35:56.551592+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTJU254KVK7X","created_at":"2026-07-05T08:35:56.551592+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTJU254KVK7X2VE4","created_at":"2026-07-05T08:35:56.551592+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTJU254K","created_at":"2026-07-05T08:35:56.551592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03168","citing_title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTJU254KVK7X2VE4N5CIS6SXXS","json":"https://pith.science/pith/HTJU254KVK7X2VE4N5CIS6SXXS.json","graph_json":"https://pith.science/api/pith-number/HTJU254KVK7X2VE4N5CIS6SXXS/graph.json","events_json":"https://pith.science/api/pith-number/HTJU254KVK7X2VE4N5CIS6SXXS/events.json","paper":"https://pith.science/paper/HTJU254K"},"agent_actions":{"view_html":"https://pith.science/pith/HTJU254KVK7X2VE4N5CIS6SXXS","download_json":"https://pith.science/pith/HTJU254KVK7X2VE4N5CIS6SXXS.json","view_paper":"https://pith.science/paper/HTJU254K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16314&json=true","fetch_graph":"https://pith.science/api/pith-number/HTJU254KVK7X2VE4N5CIS6SXXS/graph.json","fetch_events":"https://pith.science/api/pith-number/HTJU254KVK7X2VE4N5CIS6SXXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTJU254KVK7X2VE4N5CIS6SXXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTJU254KVK7X2VE4N5CIS6SXXS/action/storage_attestation","attest_author":"https://pith.science/pith/HTJU254KVK7X2VE4N5CIS6SXXS/action/author_attestation","sign_citation":"https://pith.science/pith/HTJU254KVK7X2VE4N5CIS6SXXS/action/citation_signature","submit_replication":"https://pith.science/pith/HTJU254KVK7X2VE4N5CIS6SXXS/action/replication_record"}},"created_at":"2026-07-05T08:35:56.551592+00:00","updated_at":"2026-07-05T08:35:56.551592+00:00"}