{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ND7MQUX3VMSYQ2A4F7YSH6NIW4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d3d7b041a180a0803caca008d899b32146acfb52cf052d22a3e39dec3718628b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-29T11:26:56Z","title_canon_sha256":"cc9d466ff04ef1198d5669999a92ad8e047edcff2bae463ba9af8d3599c15c7c"},"schema_version":"1.0","source":{"id":"2203.15447","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.15447","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2203.15447v2","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15447","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"ND7MQUX3VMSY","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"ND7MQUX3VMSYQ2A4","created_at":"2026-07-05T05:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"ND7MQUX3","created_at":"2026-07-05T05:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:24c03a772c811060e6f006b3f9b430706ac597be0e4ebe02d077ce02cbf0b82e","target":"graph","created_at":"2026-07-05T05:03:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.15447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a text-to-speech (TTS) model requires a large scale text labeled speech corpus, which is troublesome to collect. In this paper, we propose a transfer learning framework for TTS that utilizes a large amount of unlabeled speech dataset for pre-training. By leveraging wav2vec2.0 representation, unlabeled speech can highly improve performance, especially in the lack of labeled speech. We also extend the proposed method to zero-shot multi-speaker TTS (ZS-TTS). The experimental results verify the effectiveness of the proposed method in terms of naturalness, intelligibility, and speaker gene","authors_text":"Byoung Jin Choi, Joun Yeop Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim, Sunghwan Ahn","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-29T11:26:56Z","title":"Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15447","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:89643e6db0d56a18c0f3fddc89e997bf7719886954bf04939b1a68f7b1c4da42","target":"record","created_at":"2026-07-05T05:03:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d3d7b041a180a0803caca008d899b32146acfb52cf052d22a3e39dec3718628b","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-29T11:26:56Z","title_canon_sha256":"cc9d466ff04ef1198d5669999a92ad8e047edcff2bae463ba9af8d3599c15c7c"},"schema_version":"1.0","source":{"id":"2203.15447","kind":"arxiv","version":2}},"canonical_sha256":"68fec852fbab2588681c2ff123f9a8b72df0840d09755f0268075c5b1022ffa5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68fec852fbab2588681c2ff123f9a8b72df0840d09755f0268075c5b1022ffa5","first_computed_at":"2026-07-05T05:03:50.664513Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:50.664513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fVOaQUYljNhBz3WHl7mzd8osJd4R/dbuiPQsVujGEPoFfEBdS7c8QVXBfcn+g+I4NgwLUlsPaQTxrBJKkPnWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:50.665021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.15447","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89643e6db0d56a18c0f3fddc89e997bf7719886954bf04939b1a68f7b1c4da42","sha256:24c03a772c811060e6f006b3f9b430706ac597be0e4ebe02d077ce02cbf0b82e"],"state_sha256":"8e8ffba5c193dc20a992e4d5b63d3bc515ff92a51cfee19c8713557f1c0d66dc"}