{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ND7MQUX3VMSYQ2A4F7YSH6NIW4","short_pith_number":"pith:ND7MQUX3","schema_version":"1.0","canonical_sha256":"68fec852fbab2588681c2ff123f9a8b72df0840d09755f0268075c5b1022ffa5","source":{"kind":"arxiv","id":"2203.15447","version":2},"attestation_state":"computed","paper":{"title":"Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Joun Yeop Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim, Sunghwan Ahn","submitted_at":"2022-03-29T11:26:56Z","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"},"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":"2203.15447","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-03-29T11:26:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cc9d466ff04ef1198d5669999a92ad8e047edcff2bae463ba9af8d3599c15c7c","abstract_canon_sha256":"d3d7b041a180a0803caca008d899b32146acfb52cf052d22a3e39dec3718628b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:50.665021Z","signature_b64":"fVOaQUYljNhBz3WHl7mzd8osJd4R/dbuiPQsVujGEPoFfEBdS7c8QVXBfcn+g+I4NgwLUlsPaQTxrBJKkPnWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68fec852fbab2588681c2ff123f9a8b72df0840d09755f0268075c5b1022ffa5","last_reissued_at":"2026-07-05T05:03:50.664513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:50.664513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transfer Learning Framework for Low-Resource Text-to-Speech using a Large-Scale Unlabeled Speech Corpus","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Joun Yeop Lee, Minchan Kim, Myeonghun Jeong, Nam Soo Kim, Sunghwan Ahn","submitted_at":"2022-03-29T11:26:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.15447","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/2203.15447/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":"2203.15447","created_at":"2026-07-05T05:03:50.664582+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.15447v2","created_at":"2026-07-05T05:03:50.664582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.15447","created_at":"2026-07-05T05:03:50.664582+00:00"},{"alias_kind":"pith_short_12","alias_value":"ND7MQUX3VMSY","created_at":"2026-07-05T05:03:50.664582+00:00"},{"alias_kind":"pith_short_16","alias_value":"ND7MQUX3VMSYQ2A4","created_at":"2026-07-05T05:03:50.664582+00:00"},{"alias_kind":"pith_short_8","alias_value":"ND7MQUX3","created_at":"2026-07-05T05:03:50.664582+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/ND7MQUX3VMSYQ2A4F7YSH6NIW4","json":"https://pith.science/pith/ND7MQUX3VMSYQ2A4F7YSH6NIW4.json","graph_json":"https://pith.science/api/pith-number/ND7MQUX3VMSYQ2A4F7YSH6NIW4/graph.json","events_json":"https://pith.science/api/pith-number/ND7MQUX3VMSYQ2A4F7YSH6NIW4/events.json","paper":"https://pith.science/paper/ND7MQUX3"},"agent_actions":{"view_html":"https://pith.science/pith/ND7MQUX3VMSYQ2A4F7YSH6NIW4","download_json":"https://pith.science/pith/ND7MQUX3VMSYQ2A4F7YSH6NIW4.json","view_paper":"https://pith.science/paper/ND7MQUX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.15447&json=true","fetch_graph":"https://pith.science/api/pith-number/ND7MQUX3VMSYQ2A4F7YSH6NIW4/graph.json","fetch_events":"https://pith.science/api/pith-number/ND7MQUX3VMSYQ2A4F7YSH6NIW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ND7MQUX3VMSYQ2A4F7YSH6NIW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ND7MQUX3VMSYQ2A4F7YSH6NIW4/action/storage_attestation","attest_author":"https://pith.science/pith/ND7MQUX3VMSYQ2A4F7YSH6NIW4/action/author_attestation","sign_citation":"https://pith.science/pith/ND7MQUX3VMSYQ2A4F7YSH6NIW4/action/citation_signature","submit_replication":"https://pith.science/pith/ND7MQUX3VMSYQ2A4F7YSH6NIW4/action/replication_record"}},"created_at":"2026-07-05T05:03:50.664582+00:00","updated_at":"2026-07-05T05:03:50.664582+00:00"}