{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MLE442ZAPQ65TYINYNSESAU6IO","short_pith_number":"pith:MLE442ZA","schema_version":"1.0","canonical_sha256":"62c9ce6b207c3dd9e10dc36449029e43b030e7ae4685ec00511019e88d30e7fc","source":{"kind":"arxiv","id":"2409.10058","version":1},"attestation_state":"computed","paper":{"title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","submitted_at":"2024-09-16T07:39:58Z","abstract_excerpt":"The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, reliance on complex pre-trained neural codec representations, and difficulties in achieving naturalness and high similarity to reference speakers. To address these challenges, this work introduces StyleTTS-ZS, an efficient zero-shot TTS model that leverages distilled time-varying style diffusion to capture diverse speaker identities and prosodies. We propose a novel approach th"},"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":"2409.10058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T07:39:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8981384a9babfe73a9372315702ebdf4405676c4637028d6ec8eec13ed7d5827","abstract_canon_sha256":"7f1dff23ce4d23deab383ad206ab9e03585abb24708c8af18b59afae2e9bc9e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:34.079106Z","signature_b64":"kNenfH6T25BKGHLs5b2OEqOYh6Gr2DaKXMQd9IIJ9CrDVbwpET3rTjI9aTo9qPX/zL+hevotcNGEyAd8WJPHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c9ce6b207c3dd9e10dc36449029e43b030e7ae4685ec00511019e88d30e7fc","last_reissued_at":"2026-07-05T09:07:34.078630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:34.078630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","submitted_at":"2024-09-16T07:39:58Z","abstract_excerpt":"The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, reliance on complex pre-trained neural codec representations, and difficulties in achieving naturalness and high similarity to reference speakers. To address these challenges, this work introduces StyleTTS-ZS, an efficient zero-shot TTS model that leverages distilled time-varying style diffusion to capture diverse speaker identities and prosodies. We propose a novel approach th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10058","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/2409.10058/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":"2409.10058","created_at":"2026-07-05T09:07:34.078686+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10058v1","created_at":"2026-07-05T09:07:34.078686+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10058","created_at":"2026-07-05T09:07:34.078686+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLE442ZAPQ65","created_at":"2026-07-05T09:07:34.078686+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLE442ZAPQ65TYIN","created_at":"2026-07-05T09:07:34.078686+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLE442ZA","created_at":"2026-07-05T09:07:34.078686+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/MLE442ZAPQ65TYINYNSESAU6IO","json":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO.json","graph_json":"https://pith.science/api/pith-number/MLE442ZAPQ65TYINYNSESAU6IO/graph.json","events_json":"https://pith.science/api/pith-number/MLE442ZAPQ65TYINYNSESAU6IO/events.json","paper":"https://pith.science/paper/MLE442ZA"},"agent_actions":{"view_html":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO","download_json":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO.json","view_paper":"https://pith.science/paper/MLE442ZA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10058&json=true","fetch_graph":"https://pith.science/api/pith-number/MLE442ZAPQ65TYINYNSESAU6IO/graph.json","fetch_events":"https://pith.science/api/pith-number/MLE442ZAPQ65TYINYNSESAU6IO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO/action/storage_attestation","attest_author":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO/action/author_attestation","sign_citation":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO/action/citation_signature","submit_replication":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO/action/replication_record"}},"created_at":"2026-07-05T09:07:34.078686+00:00","updated_at":"2026-07-05T09:07:34.078686+00:00"}