{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HJSVNFU7IRRZM73IE7K5AQNNI5","short_pith_number":"pith:HJSVNFU7","schema_version":"1.0","canonical_sha256":"3a6556969f4463967f6827d5d041ad47440fd35701604768c090838ebd500a76","source":{"kind":"arxiv","id":"2505.11200","version":1},"attestation_state":"computed","paper":{"title":"Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guanglu Wan, Lin Qiu, Shao Zhang, Siyu Ren, Song Li, Weinan Zhang, Xiaoyu Li, Xihuai Wang, Xuezhi Cao, Xunliang Cai, Ziwen Wang, Ziyi Zhao","submitted_at":"2025-05-16T12:57:23Z","abstract_excerpt":"Recent advances in large language models (LLMs) have significantly improved text-to-speech (TTS) systems, enhancing control over speech style, naturalness, and emotional expression, which brings TTS Systems closer to human-level performance. Although the Mean Opinion Score (MOS) remains the standard for TTS System evaluation, it suffers from subjectivity, environmental inconsistencies, and limited interpretability. Existing evaluation datasets also lack a multi-dimensional design, often neglecting factors such as speaking styles, context diversity, and trap utterances, which is particularly ev"},"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":"2505.11200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-16T12:57:23Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC","cs.LG","eess.AS"],"title_canon_sha256":"67a2e27e44664e24a58a10f782c06a89570205557ac636e8b924a6cd5dd7a655","abstract_canon_sha256":"437ba93f3410a8423d29d60b44efb7ee02a94a42f4a0c50e80dc67571d2f3695"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:12.649935Z","signature_b64":"pZDP5Kyn6XpW6HCOZAMBk5nT7Kab6/7Un9b4Ss5WNaYY2zZV881apIPBb6MBU02iHhBKj35bdVR5r9+f2PpjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a6556969f4463967f6827d5d041ad47440fd35701604768c090838ebd500a76","last_reissued_at":"2026-07-05T11:04:12.649410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:12.649410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guanglu Wan, Lin Qiu, Shao Zhang, Siyu Ren, Song Li, Weinan Zhang, Xiaoyu Li, Xihuai Wang, Xuezhi Cao, Xunliang Cai, Ziwen Wang, Ziyi Zhao","submitted_at":"2025-05-16T12:57:23Z","abstract_excerpt":"Recent advances in large language models (LLMs) have significantly improved text-to-speech (TTS) systems, enhancing control over speech style, naturalness, and emotional expression, which brings TTS Systems closer to human-level performance. Although the Mean Opinion Score (MOS) remains the standard for TTS System evaluation, it suffers from subjectivity, environmental inconsistencies, and limited interpretability. Existing evaluation datasets also lack a multi-dimensional design, often neglecting factors such as speaking styles, context diversity, and trap utterances, which is particularly ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11200","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/2505.11200/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":"2505.11200","created_at":"2026-07-05T11:04:12.649472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11200v1","created_at":"2026-07-05T11:04:12.649472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11200","created_at":"2026-07-05T11:04:12.649472+00:00"},{"alias_kind":"pith_short_12","alias_value":"HJSVNFU7IRRZ","created_at":"2026-07-05T11:04:12.649472+00:00"},{"alias_kind":"pith_short_16","alias_value":"HJSVNFU7IRRZM73I","created_at":"2026-07-05T11:04:12.649472+00:00"},{"alias_kind":"pith_short_8","alias_value":"HJSVNFU7","created_at":"2026-07-05T11:04:12.649472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22225","citing_title":"TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HJSVNFU7IRRZM73IE7K5AQNNI5","json":"https://pith.science/pith/HJSVNFU7IRRZM73IE7K5AQNNI5.json","graph_json":"https://pith.science/api/pith-number/HJSVNFU7IRRZM73IE7K5AQNNI5/graph.json","events_json":"https://pith.science/api/pith-number/HJSVNFU7IRRZM73IE7K5AQNNI5/events.json","paper":"https://pith.science/paper/HJSVNFU7"},"agent_actions":{"view_html":"https://pith.science/pith/HJSVNFU7IRRZM73IE7K5AQNNI5","download_json":"https://pith.science/pith/HJSVNFU7IRRZM73IE7K5AQNNI5.json","view_paper":"https://pith.science/paper/HJSVNFU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11200&json=true","fetch_graph":"https://pith.science/api/pith-number/HJSVNFU7IRRZM73IE7K5AQNNI5/graph.json","fetch_events":"https://pith.science/api/pith-number/HJSVNFU7IRRZM73IE7K5AQNNI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HJSVNFU7IRRZM73IE7K5AQNNI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HJSVNFU7IRRZM73IE7K5AQNNI5/action/storage_attestation","attest_author":"https://pith.science/pith/HJSVNFU7IRRZM73IE7K5AQNNI5/action/author_attestation","sign_citation":"https://pith.science/pith/HJSVNFU7IRRZM73IE7K5AQNNI5/action/citation_signature","submit_replication":"https://pith.science/pith/HJSVNFU7IRRZM73IE7K5AQNNI5/action/replication_record"}},"created_at":"2026-07-05T11:04:12.649472+00:00","updated_at":"2026-07-05T11:04:12.649472+00:00"}