{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5NBVBJC6G2E7QZKSC3NYKSNARH","short_pith_number":"pith:5NBVBJC6","schema_version":"1.0","canonical_sha256":"eb4350a45e3689f8655216db8549a089c0435a32a7cbb9ccc52089ae1a890420","source":{"kind":"arxiv","id":"2106.03153","version":3},"attestation_state":"computed","paper":{"title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dong Bok Lee, Dongchan Min, Eunho Yang, Sung Ju Hwang","submitted_at":"2021-06-06T15:34:11Z","abstract_excerpt":"With rapid progress in neural text-to-speech (TTS) models, personalized speech generation is now in high demand for many applications. For practical applicability, a TTS model should generate high-quality speech with only a few audio samples from the given speaker, that are also short in length. However, existing methods either require to fine-tune the model or achieve low adaptation quality without fine-tuning. In this work, we propose StyleSpeech, a new TTS model which not only synthesizes high-quality speech but also effectively adapts to new speakers. Specifically, we propose Style-Adaptiv"},"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":"2106.03153","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-06-06T15:34:11Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"86e8a23a655a70bd3fa280bb5feaaab0d23c2156a93513fffbe387b773f3f4be","abstract_canon_sha256":"0c047bf44f2d20a6e9eca413f900cc58406919b423278448f02e6695935b9404"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:55.522895Z","signature_b64":"sREx5tZNxZvUDBnbrhDzl6+mU4XVWbirMKRuxiFhHde+sroLKA46Eg59yZ7+f+RPok3bZR01SKXrFAKH4+PIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb4350a45e3689f8655216db8549a089c0435a32a7cbb9ccc52089ae1a890420","last_reissued_at":"2026-07-05T02:49:55.522435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:55.522435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dong Bok Lee, Dongchan Min, Eunho Yang, Sung Ju Hwang","submitted_at":"2021-06-06T15:34:11Z","abstract_excerpt":"With rapid progress in neural text-to-speech (TTS) models, personalized speech generation is now in high demand for many applications. For practical applicability, a TTS model should generate high-quality speech with only a few audio samples from the given speaker, that are also short in length. However, existing methods either require to fine-tune the model or achieve low adaptation quality without fine-tuning. In this work, we propose StyleSpeech, a new TTS model which not only synthesizes high-quality speech but also effectively adapts to new speakers. Specifically, we propose Style-Adaptiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03153","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/2106.03153/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":"2106.03153","created_at":"2026-07-05T02:49:55.522496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03153v3","created_at":"2026-07-05T02:49:55.522496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03153","created_at":"2026-07-05T02:49:55.522496+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NBVBJC6G2E7","created_at":"2026-07-05T02:49:55.522496+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NBVBJC6G2E7QZKS","created_at":"2026-07-05T02:49:55.522496+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NBVBJC6","created_at":"2026-07-05T02:49:55.522496+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/5NBVBJC6G2E7QZKSC3NYKSNARH","json":"https://pith.science/pith/5NBVBJC6G2E7QZKSC3NYKSNARH.json","graph_json":"https://pith.science/api/pith-number/5NBVBJC6G2E7QZKSC3NYKSNARH/graph.json","events_json":"https://pith.science/api/pith-number/5NBVBJC6G2E7QZKSC3NYKSNARH/events.json","paper":"https://pith.science/paper/5NBVBJC6"},"agent_actions":{"view_html":"https://pith.science/pith/5NBVBJC6G2E7QZKSC3NYKSNARH","download_json":"https://pith.science/pith/5NBVBJC6G2E7QZKSC3NYKSNARH.json","view_paper":"https://pith.science/paper/5NBVBJC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03153&json=true","fetch_graph":"https://pith.science/api/pith-number/5NBVBJC6G2E7QZKSC3NYKSNARH/graph.json","fetch_events":"https://pith.science/api/pith-number/5NBVBJC6G2E7QZKSC3NYKSNARH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NBVBJC6G2E7QZKSC3NYKSNARH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NBVBJC6G2E7QZKSC3NYKSNARH/action/storage_attestation","attest_author":"https://pith.science/pith/5NBVBJC6G2E7QZKSC3NYKSNARH/action/author_attestation","sign_citation":"https://pith.science/pith/5NBVBJC6G2E7QZKSC3NYKSNARH/action/citation_signature","submit_replication":"https://pith.science/pith/5NBVBJC6G2E7QZKSC3NYKSNARH/action/replication_record"}},"created_at":"2026-07-05T02:49:55.522496+00:00","updated_at":"2026-07-05T02:49:55.522496+00:00"}