{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7657CZJRRALHC4UJSKCRB3SGSL","short_pith_number":"pith:7657CZJR","schema_version":"1.0","canonical_sha256":"ffbbf165318816717289928510ee4692f0fc0f411a887bd04d99f6558fdbe8f0","source":{"kind":"arxiv","id":"2309.00126","version":1},"attestation_state":"computed","paper":{"title":"QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fenglong Xie, Haohan Guo, Helen Meng, Jiawen Kang, Xixin Wu, Yujia Xiao","submitted_at":"2023-08-31T20:25:44Z","abstract_excerpt":"This paper proposes a novel semi-supervised TTS framework, QS-TTS, to improve TTS quality with lower supervised data requirements via Vector-Quantized Self-Supervised Speech Representation Learning (VQ-S3RL) utilizing more unlabeled speech audio. This framework comprises two VQ-S3R learners: first, the principal learner aims to provide a generative Multi-Stage Multi-Codebook (MSMC) VQ-S3R via the MSMC-VQ-GAN combined with the contrastive S3RL, while decoding it back to the high-quality audio; then, the associate learner further abstracts the MSMC representation into a highly-compact VQ represe"},"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":"2309.00126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-31T20:25:44Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"49a18cbad35ca166e7d460b60003bc6d282bc857473160443df803fcc0c8962a","abstract_canon_sha256":"358298a934690425bb4591593a8028afcce29b21b32bf1c4d0cc65dd064ca1b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:52.618114Z","signature_b64":"Q0CSwQv8Evu+b71iKHwlthgH2ZMVXId8j+F5doIHfXCdZ/70ypKa6HwTopVjeRl9sykh3/66XhX1Aq5/tYndBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffbbf165318816717289928510ee4692f0fc0f411a887bd04d99f6558fdbe8f0","last_reissued_at":"2026-07-05T06:46:52.617645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:52.617645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fenglong Xie, Haohan Guo, Helen Meng, Jiawen Kang, Xixin Wu, Yujia Xiao","submitted_at":"2023-08-31T20:25:44Z","abstract_excerpt":"This paper proposes a novel semi-supervised TTS framework, QS-TTS, to improve TTS quality with lower supervised data requirements via Vector-Quantized Self-Supervised Speech Representation Learning (VQ-S3RL) utilizing more unlabeled speech audio. This framework comprises two VQ-S3R learners: first, the principal learner aims to provide a generative Multi-Stage Multi-Codebook (MSMC) VQ-S3R via the MSMC-VQ-GAN combined with the contrastive S3RL, while decoding it back to the high-quality audio; then, the associate learner further abstracts the MSMC representation into a highly-compact VQ represe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00126","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/2309.00126/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":"2309.00126","created_at":"2026-07-05T06:46:52.617702+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.00126v1","created_at":"2026-07-05T06:46:52.617702+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00126","created_at":"2026-07-05T06:46:52.617702+00:00"},{"alias_kind":"pith_short_12","alias_value":"7657CZJRRALH","created_at":"2026-07-05T06:46:52.617702+00:00"},{"alias_kind":"pith_short_16","alias_value":"7657CZJRRALHC4UJ","created_at":"2026-07-05T06:46:52.617702+00:00"},{"alias_kind":"pith_short_8","alias_value":"7657CZJR","created_at":"2026-07-05T06:46:52.617702+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/7657CZJRRALHC4UJSKCRB3SGSL","json":"https://pith.science/pith/7657CZJRRALHC4UJSKCRB3SGSL.json","graph_json":"https://pith.science/api/pith-number/7657CZJRRALHC4UJSKCRB3SGSL/graph.json","events_json":"https://pith.science/api/pith-number/7657CZJRRALHC4UJSKCRB3SGSL/events.json","paper":"https://pith.science/paper/7657CZJR"},"agent_actions":{"view_html":"https://pith.science/pith/7657CZJRRALHC4UJSKCRB3SGSL","download_json":"https://pith.science/pith/7657CZJRRALHC4UJSKCRB3SGSL.json","view_paper":"https://pith.science/paper/7657CZJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.00126&json=true","fetch_graph":"https://pith.science/api/pith-number/7657CZJRRALHC4UJSKCRB3SGSL/graph.json","fetch_events":"https://pith.science/api/pith-number/7657CZJRRALHC4UJSKCRB3SGSL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7657CZJRRALHC4UJSKCRB3SGSL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7657CZJRRALHC4UJSKCRB3SGSL/action/storage_attestation","attest_author":"https://pith.science/pith/7657CZJRRALHC4UJSKCRB3SGSL/action/author_attestation","sign_citation":"https://pith.science/pith/7657CZJRRALHC4UJSKCRB3SGSL/action/citation_signature","submit_replication":"https://pith.science/pith/7657CZJRRALHC4UJSKCRB3SGSL/action/replication_record"}},"created_at":"2026-07-05T06:46:52.617702+00:00","updated_at":"2026-07-05T06:46:52.617702+00:00"}