{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5KA5W7L4YELJLBM3MPLE5MAR4V","short_pith_number":"pith:5KA5W7L4","schema_version":"1.0","canonical_sha256":"ea81db7d7cc11695859b63d64eb011e572c19098725ed733cc27fa8e5299222b","source":{"kind":"arxiv","id":"2306.07547","version":6},"attestation_state":"computed","paper":{"title":"UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenpeng Du, Feiyu Shen, Hui Zhang, Kai Yu, Shuai Wang, Xie Chen, Yiwei Guo, Zheng Liang, Zhijun Liu","submitted_at":"2023-06-13T05:38:34Z","abstract_excerpt":"The utilization of discrete speech tokens, divided into semantic tokens and acoustic tokens, has been proven superior to traditional acoustic feature mel-spectrograms in terms of naturalness and robustness for text-to-speech (TTS) synthesis. Recent popular models, such as VALL-E and SPEAR-TTS, allow zero-shot speaker adaptation through auto-regressive (AR) continuation of acoustic tokens extracted from a short speech prompt. However, these AR models are restricted to generate speech only in a left-to-right direction, making them unsuitable for speech editing where both preceding and following "},"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":"2306.07547","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-13T05:38:34Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"ce75b6a06e94713a76eeb278558eccc2bdd0d65aff4330539b3adf7fdc376f3f","abstract_canon_sha256":"2d3cc83d0b1110bc4a966dbfc35110241fd92d12cf2f38f30fa110c826d2f381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:30.588416Z","signature_b64":"IN8BsHzDH+B8zq8s5aC72g25pbmicMxUE8kLeieP9CQeXp8zHbO3C+bYBGGnDeG6llqIw639oO3Mmn7fK1g9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea81db7d7cc11695859b63d64eb011e572c19098725ed733cc27fa8e5299222b","last_reissued_at":"2026-07-05T08:01:30.587969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:30.587969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenpeng Du, Feiyu Shen, Hui Zhang, Kai Yu, Shuai Wang, Xie Chen, Yiwei Guo, Zheng Liang, Zhijun Liu","submitted_at":"2023-06-13T05:38:34Z","abstract_excerpt":"The utilization of discrete speech tokens, divided into semantic tokens and acoustic tokens, has been proven superior to traditional acoustic feature mel-spectrograms in terms of naturalness and robustness for text-to-speech (TTS) synthesis. Recent popular models, such as VALL-E and SPEAR-TTS, allow zero-shot speaker adaptation through auto-regressive (AR) continuation of acoustic tokens extracted from a short speech prompt. However, these AR models are restricted to generate speech only in a left-to-right direction, making them unsuitable for speech editing where both preceding and following "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07547","kind":"arxiv","version":6},"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/2306.07547/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":"2306.07547","created_at":"2026-07-05T08:01:30.588022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07547v6","created_at":"2026-07-05T08:01:30.588022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07547","created_at":"2026-07-05T08:01:30.588022+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KA5W7L4YELJ","created_at":"2026-07-05T08:01:30.588022+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KA5W7L4YELJLBM3","created_at":"2026-07-05T08:01:30.588022+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KA5W7L4","created_at":"2026-07-05T08:01:30.588022+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/5KA5W7L4YELJLBM3MPLE5MAR4V","json":"https://pith.science/pith/5KA5W7L4YELJLBM3MPLE5MAR4V.json","graph_json":"https://pith.science/api/pith-number/5KA5W7L4YELJLBM3MPLE5MAR4V/graph.json","events_json":"https://pith.science/api/pith-number/5KA5W7L4YELJLBM3MPLE5MAR4V/events.json","paper":"https://pith.science/paper/5KA5W7L4"},"agent_actions":{"view_html":"https://pith.science/pith/5KA5W7L4YELJLBM3MPLE5MAR4V","download_json":"https://pith.science/pith/5KA5W7L4YELJLBM3MPLE5MAR4V.json","view_paper":"https://pith.science/paper/5KA5W7L4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07547&json=true","fetch_graph":"https://pith.science/api/pith-number/5KA5W7L4YELJLBM3MPLE5MAR4V/graph.json","fetch_events":"https://pith.science/api/pith-number/5KA5W7L4YELJLBM3MPLE5MAR4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KA5W7L4YELJLBM3MPLE5MAR4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KA5W7L4YELJLBM3MPLE5MAR4V/action/storage_attestation","attest_author":"https://pith.science/pith/5KA5W7L4YELJLBM3MPLE5MAR4V/action/author_attestation","sign_citation":"https://pith.science/pith/5KA5W7L4YELJLBM3MPLE5MAR4V/action/citation_signature","submit_replication":"https://pith.science/pith/5KA5W7L4YELJLBM3MPLE5MAR4V/action/replication_record"}},"created_at":"2026-07-05T08:01:30.588022+00:00","updated_at":"2026-07-05T08:01:30.588022+00:00"}