{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WIDG2KLUX4SA4EBOGIGQOCLGXD","short_pith_number":"pith:WIDG2KLU","schema_version":"1.0","canonical_sha256":"b2066d2974bf240e102e320d070966b8ddeb617f801c4758d70718fbee264af7","source":{"kind":"arxiv","id":"2406.00654","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Chen Chen, Eng Siong Chng, Helin Wang, Wen Wu, Yuchen Hu","submitted_at":"2024-06-02T07:54:33Z","abstract_excerpt":"In recent years, text-to-speech (TTS) technology has witnessed impressive advancements, particularly with large-scale training datasets, showcasing human-level speech quality and impressive zero-shot capabilities on unseen speakers. However, despite human subjective evaluations, such as the mean opinion score (MOS), remaining the gold standard for assessing the quality of synthetic speech, even state-of-the-art TTS approaches have kept human feedback isolated from training that resulted in mismatched training objectives and evaluation metrics. In this work, we investigate a novel topic of inte"},"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":"2406.00654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T07:54:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"aa3f20e87e5d4f3aa7269035a74634544cf5aefecd4c25edbfb9a2edcf76b328","abstract_canon_sha256":"1c427e55309e19bd7fe12e9d6f452fbf31ec8ea0f9ae32e463054d83640ed40d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:28.727053Z","signature_b64":"qduxxoazGlOzJg4/ZLlJ7UK4fLF1/yyRwIH/oseeYnQH4poMyucl4vnsgdtZgALUC1yI/Epqh77HggQJI5Y6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2066d2974bf240e102e320d070966b8ddeb617f801c4758d70718fbee264af7","last_reissued_at":"2026-07-05T08:26:28.726617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:28.726617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Chen Chen, Eng Siong Chng, Helin Wang, Wen Wu, Yuchen Hu","submitted_at":"2024-06-02T07:54:33Z","abstract_excerpt":"In recent years, text-to-speech (TTS) technology has witnessed impressive advancements, particularly with large-scale training datasets, showcasing human-level speech quality and impressive zero-shot capabilities on unseen speakers. However, despite human subjective evaluations, such as the mean opinion score (MOS), remaining the gold standard for assessing the quality of synthetic speech, even state-of-the-art TTS approaches have kept human feedback isolated from training that resulted in mismatched training objectives and evaluation metrics. In this work, we investigate a novel topic of inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00654","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/2406.00654/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":"2406.00654","created_at":"2026-07-05T08:26:28.726668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00654v1","created_at":"2026-07-05T08:26:28.726668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00654","created_at":"2026-07-05T08:26:28.726668+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIDG2KLUX4SA","created_at":"2026-07-05T08:26:28.726668+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIDG2KLUX4SA4EBO","created_at":"2026-07-05T08:26:28.726668+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIDG2KLU","created_at":"2026-07-05T08:26:28.726668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.05373","citing_title":"Hierarchical Decoding for Discrete Speech Synthesis with Multi-Resolution Spoof Detection","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD","json":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD.json","graph_json":"https://pith.science/api/pith-number/WIDG2KLUX4SA4EBOGIGQOCLGXD/graph.json","events_json":"https://pith.science/api/pith-number/WIDG2KLUX4SA4EBOGIGQOCLGXD/events.json","paper":"https://pith.science/paper/WIDG2KLU"},"agent_actions":{"view_html":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD","download_json":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD.json","view_paper":"https://pith.science/paper/WIDG2KLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00654&json=true","fetch_graph":"https://pith.science/api/pith-number/WIDG2KLUX4SA4EBOGIGQOCLGXD/graph.json","fetch_events":"https://pith.science/api/pith-number/WIDG2KLUX4SA4EBOGIGQOCLGXD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/action/storage_attestation","attest_author":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/action/author_attestation","sign_citation":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/action/citation_signature","submit_replication":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/action/replication_record"}},"created_at":"2026-07-05T08:26:28.726668+00:00","updated_at":"2026-07-05T08:26:28.726668+00:00"}