{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:KDJTNWOWWXPHOSK5UWVZ4FYP6H","short_pith_number":"pith:KDJTNWOW","schema_version":"1.0","canonical_sha256":"50d336d9d6b5de77495da5ab9e170ff1c4a4107e1fed42aa90fa33d09e31aa47","source":{"kind":"arxiv","id":"2211.09383","version":2},"attestation_state":"computed","paper":{"title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongchan Min, Minki Kang, Sung Ju Hwang","submitted_at":"2022-11-17T07:17:24Z","abstract_excerpt":"There has been a significant progress in Text-To-Speech (TTS) synthesis technology in recent years, thanks to the advancement in neural generative modeling. However, existing methods on any-speaker adaptive TTS have achieved unsatisfactory performance, due to their suboptimal accuracy in mimicking the target speakers' styles. In this work, we present Grad-StyleSpeech, which is an any-speaker adaptive TTS framework that is based on a diffusion model that can generate highly natural speech with extremely high similarity to target speakers' voice, given a few seconds of reference speech. Grad-Sty"},"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":"2211.09383","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-17T07:17:24Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"8f3714c8a258981a0268b8426eaa4fdd6dc49a42fa174fe993ced476f554258a","abstract_canon_sha256":"dde767141ea7cad3bdbd5da8efb61fcc19ac61bd29521cdd01b7bdce4f7340a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:52.945134Z","signature_b64":"E8vyuSiicEkbjmrBZvyHSDek/fEo9S0rQfkNOoGZVT2viyVhvvFHxd5A6Nv8yR7HpsX1yPXXF2xQHJTZo1ITAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d336d9d6b5de77495da5ab9e170ff1c4a4107e1fed42aa90fa33d09e31aa47","last_reissued_at":"2026-07-05T05:50:52.944718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:52.944718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongchan Min, Minki Kang, Sung Ju Hwang","submitted_at":"2022-11-17T07:17:24Z","abstract_excerpt":"There has been a significant progress in Text-To-Speech (TTS) synthesis technology in recent years, thanks to the advancement in neural generative modeling. However, existing methods on any-speaker adaptive TTS have achieved unsatisfactory performance, due to their suboptimal accuracy in mimicking the target speakers' styles. In this work, we present Grad-StyleSpeech, which is an any-speaker adaptive TTS framework that is based on a diffusion model that can generate highly natural speech with extremely high similarity to target speakers' voice, given a few seconds of reference speech. Grad-Sty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09383","kind":"arxiv","version":2},"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/2211.09383/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":"2211.09383","created_at":"2026-07-05T05:50:52.944774+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09383v2","created_at":"2026-07-05T05:50:52.944774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09383","created_at":"2026-07-05T05:50:52.944774+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDJTNWOWWXPH","created_at":"2026-07-05T05:50:52.944774+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDJTNWOWWXPHOSK5","created_at":"2026-07-05T05:50:52.944774+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDJTNWOW","created_at":"2026-07-05T05:50:52.944774+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2306.14289","citing_title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2301.02111","citing_title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2301.02111","citing_title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H","json":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H.json","graph_json":"https://pith.science/api/pith-number/KDJTNWOWWXPHOSK5UWVZ4FYP6H/graph.json","events_json":"https://pith.science/api/pith-number/KDJTNWOWWXPHOSK5UWVZ4FYP6H/events.json","paper":"https://pith.science/paper/KDJTNWOW"},"agent_actions":{"view_html":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H","download_json":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H.json","view_paper":"https://pith.science/paper/KDJTNWOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09383&json=true","fetch_graph":"https://pith.science/api/pith-number/KDJTNWOWWXPHOSK5UWVZ4FYP6H/graph.json","fetch_events":"https://pith.science/api/pith-number/KDJTNWOWWXPHOSK5UWVZ4FYP6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/action/storage_attestation","attest_author":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/action/author_attestation","sign_citation":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/action/citation_signature","submit_replication":"https://pith.science/pith/KDJTNWOWWXPHOSK5UWVZ4FYP6H/action/replication_record"}},"created_at":"2026-07-05T05:50:52.944774+00:00","updated_at":"2026-07-05T05:50:52.944774+00:00"}