{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BY7WBMERJ27V4CNI4GCGL6POM4","short_pith_number":"pith:BY7WBMER","schema_version":"1.0","canonical_sha256":"0e3f60b0914ebf5e09a8e18465f9ee672199fa64d0d9ade1020a47639fde2356","source":{"kind":"arxiv","id":"2301.03801","version":1},"attestation_state":"computed","paper":{"title":"UnifySpeech: A Unified Framework for Zero-shot Text-to-Speech and Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haogeng Liu, Jiangyan Yi, Jianhua Tao, Ruibo Fu, Tao Wang, Zhengqi Wen","submitted_at":"2023-01-10T06:06:57Z","abstract_excerpt":"Text-to-speech (TTS) and voice conversion (VC) are two different tasks both aiming at generating high quality speaking voice according to different input modality. Due to their similarity, this paper proposes UnifySpeech, which brings TTS and VC into a unified framework for the first time. The model is based on the assumption that speech can be decoupled into three independent components: content information, speaker information, prosody information. Both TTS and VC can be regarded as mining these three parts of information from the input and completing the reconstruction of speech. For TTS, t"},"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":"2301.03801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-01-10T06:06:57Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"05d7aaf3e22f9f3a19ca26596ec501e37d7818fa14b936f826123abbb2dc4448","abstract_canon_sha256":"d905eb0a6d9b84e1cae70764232ac88ec17173cf38ac07d4b071914590cf352f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:32:05.861453Z","signature_b64":"qRt1/nx7SaXvtF/ZMlBUGAl0YHQoHrQ11ZP8qS3UhN2Hx0a0aunsX+9QnusFOmP6qoHOvPdHdO5AK/hj7EVBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e3f60b0914ebf5e09a8e18465f9ee672199fa64d0d9ade1020a47639fde2356","last_reissued_at":"2026-07-05T05:32:05.860973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:32:05.860973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UnifySpeech: A Unified Framework for Zero-shot Text-to-Speech and Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Haogeng Liu, Jiangyan Yi, Jianhua Tao, Ruibo Fu, Tao Wang, Zhengqi Wen","submitted_at":"2023-01-10T06:06:57Z","abstract_excerpt":"Text-to-speech (TTS) and voice conversion (VC) are two different tasks both aiming at generating high quality speaking voice according to different input modality. Due to their similarity, this paper proposes UnifySpeech, which brings TTS and VC into a unified framework for the first time. The model is based on the assumption that speech can be decoupled into three independent components: content information, speaker information, prosody information. Both TTS and VC can be regarded as mining these three parts of information from the input and completing the reconstruction of speech. For TTS, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.03801","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/2301.03801/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":"2301.03801","created_at":"2026-07-05T05:32:05.861035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.03801v1","created_at":"2026-07-05T05:32:05.861035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.03801","created_at":"2026-07-05T05:32:05.861035+00:00"},{"alias_kind":"pith_short_12","alias_value":"BY7WBMERJ27V","created_at":"2026-07-05T05:32:05.861035+00:00"},{"alias_kind":"pith_short_16","alias_value":"BY7WBMERJ27V4CNI","created_at":"2026-07-05T05:32:05.861035+00:00"},{"alias_kind":"pith_short_8","alias_value":"BY7WBMER","created_at":"2026-07-05T05:32:05.861035+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/BY7WBMERJ27V4CNI4GCGL6POM4","json":"https://pith.science/pith/BY7WBMERJ27V4CNI4GCGL6POM4.json","graph_json":"https://pith.science/api/pith-number/BY7WBMERJ27V4CNI4GCGL6POM4/graph.json","events_json":"https://pith.science/api/pith-number/BY7WBMERJ27V4CNI4GCGL6POM4/events.json","paper":"https://pith.science/paper/BY7WBMER"},"agent_actions":{"view_html":"https://pith.science/pith/BY7WBMERJ27V4CNI4GCGL6POM4","download_json":"https://pith.science/pith/BY7WBMERJ27V4CNI4GCGL6POM4.json","view_paper":"https://pith.science/paper/BY7WBMER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.03801&json=true","fetch_graph":"https://pith.science/api/pith-number/BY7WBMERJ27V4CNI4GCGL6POM4/graph.json","fetch_events":"https://pith.science/api/pith-number/BY7WBMERJ27V4CNI4GCGL6POM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BY7WBMERJ27V4CNI4GCGL6POM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BY7WBMERJ27V4CNI4GCGL6POM4/action/storage_attestation","attest_author":"https://pith.science/pith/BY7WBMERJ27V4CNI4GCGL6POM4/action/author_attestation","sign_citation":"https://pith.science/pith/BY7WBMERJ27V4CNI4GCGL6POM4/action/citation_signature","submit_replication":"https://pith.science/pith/BY7WBMERJ27V4CNI4GCGL6POM4/action/replication_record"}},"created_at":"2026-07-05T05:32:05.861035+00:00","updated_at":"2026-07-05T05:32:05.861035+00:00"}