{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7657CZJRRALHC4UJSKCRB3SGSL","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":"358298a934690425bb4591593a8028afcce29b21b32bf1c4d0cc65dd064ca1b8","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-31T20:25:44Z","title_canon_sha256":"49a18cbad35ca166e7d460b60003bc6d282bc857473160443df803fcc0c8962a"},"schema_version":"1.0","source":{"id":"2309.00126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.00126","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"arxiv_version","alias_value":"2309.00126v1","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00126","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"pith_short_12","alias_value":"7657CZJRRALH","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"pith_short_16","alias_value":"7657CZJRRALHC4UJ","created_at":"2026-07-05T06:46:52Z"},{"alias_kind":"pith_short_8","alias_value":"7657CZJR","created_at":"2026-07-05T06:46:52Z"}],"graph_snapshots":[{"event_id":"sha256:fdf113ee9e5956a084ffe0c0c95c94ec95f9a62e2c928742feb8680e08ee6935","target":"graph","created_at":"2026-07-05T06:46:52Z","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/2309.00126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fenglong Xie, Haohan Guo, Helen Meng, Jiawen Kang, Xixin Wu, Yujia Xiao","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-31T20:25:44Z","title":"QS-TTS: Towards Semi-Supervised Text-to-Speech Synthesis via Vector-Quantized Self-Supervised Speech Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00126","kind":"arxiv","version":1},"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":"sha256:16f92df2bb7792ff7fe78ce778fbe044c736928ae82f98a6761425cc4639dbad","target":"record","created_at":"2026-07-05T06:46:52Z","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":"358298a934690425bb4591593a8028afcce29b21b32bf1c4d0cc65dd064ca1b8","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-08-31T20:25:44Z","title_canon_sha256":"49a18cbad35ca166e7d460b60003bc6d282bc857473160443df803fcc0c8962a"},"schema_version":"1.0","source":{"id":"2309.00126","kind":"arxiv","version":1}},"canonical_sha256":"ffbbf165318816717289928510ee4692f0fc0f411a887bd04d99f6558fdbe8f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffbbf165318816717289928510ee4692f0fc0f411a887bd04d99f6558fdbe8f0","first_computed_at":"2026-07-05T06:46:52.617645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:52.617645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q0CSwQv8Evu+b71iKHwlthgH2ZMVXId8j+F5doIHfXCdZ/70ypKa6HwTopVjeRl9sykh3/66XhX1Aq5/tYndBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:52.618114Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.00126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16f92df2bb7792ff7fe78ce778fbe044c736928ae82f98a6761425cc4639dbad","sha256:fdf113ee9e5956a084ffe0c0c95c94ec95f9a62e2c928742feb8680e08ee6935"],"state_sha256":"c84d0ed5133a14e704661b6356b3f093aa5ea0c3e22891ef46a50b5973c1a213"}