{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AHS5CTR6ACJIRC3BML3PV7UMQM","short_pith_number":"pith:AHS5CTR6","schema_version":"1.0","canonical_sha256":"01e5d14e3e0092888b6162f6fafe8c830843348d94a4e487722ce983b024431f","source":{"kind":"arxiv","id":"2505.23009","version":1},"attestation_state":"computed","paper":{"title":"EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Alex Smola, Mu Li, Ruskin Raj Manku, Xingjian Shi, Yuzhi Tang","submitted_at":"2025-05-29T02:36:24Z","abstract_excerpt":"Text-to-Speech (TTS) benchmarks often fail to capture how well models handle nuanced and semantically complex text. Building on $\\textit{EmergentTTS}$, we introduce $\\textit{EmergentTTS-Eval}$, a comprehensive benchmark covering six challenging TTS scenarios: emotions, paralinguistics, foreign words, syntactic complexity, complex pronunciation (e.g. URLs, formulas), and questions. Crucially, our framework automates both test-case generation and evaluation, making the benchmark easily extensible. Starting from a small set of human-written seed prompts, we iteratively extend them using LLMs to t"},"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":"2505.23009","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T02:36:24Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"82f682087bc0131f78121c31e9aba37cf10c507438c0a9f033f43719603e36dd","abstract_canon_sha256":"9b90518760a76e194d3022ed601d9bc8ea43a1638103929a7de6b2c43700d2d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:11.841854Z","signature_b64":"KKrESkQac9oGrk628RyYrCQNdNdhYt1Fr9FYjErdBPhgdFo63Gkh9hpdnBNZSwdCSb4KnkXYxYQ1u/S2MhVqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e5d14e3e0092888b6162f6fafe8c830843348d94a4e487722ce983b024431f","last_reissued_at":"2026-07-05T11:12:11.841329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:11.841329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Alex Smola, Mu Li, Ruskin Raj Manku, Xingjian Shi, Yuzhi Tang","submitted_at":"2025-05-29T02:36:24Z","abstract_excerpt":"Text-to-Speech (TTS) benchmarks often fail to capture how well models handle nuanced and semantically complex text. Building on $\\textit{EmergentTTS}$, we introduce $\\textit{EmergentTTS-Eval}$, a comprehensive benchmark covering six challenging TTS scenarios: emotions, paralinguistics, foreign words, syntactic complexity, complex pronunciation (e.g. URLs, formulas), and questions. Crucially, our framework automates both test-case generation and evaluation, making the benchmark easily extensible. Starting from a small set of human-written seed prompts, we iteratively extend them using LLMs to t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23009","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/2505.23009/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":"2505.23009","created_at":"2026-07-05T11:12:11.841383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23009v1","created_at":"2026-07-05T11:12:11.841383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23009","created_at":"2026-07-05T11:12:11.841383+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHS5CTR6ACJI","created_at":"2026-07-05T11:12:11.841383+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHS5CTR6ACJIRC3B","created_at":"2026-07-05T11:12:11.841383+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHS5CTR6","created_at":"2026-07-05T11:12:11.841383+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31947","citing_title":"LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31947","citing_title":"LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17958","citing_title":"MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHS5CTR6ACJIRC3BML3PV7UMQM","json":"https://pith.science/pith/AHS5CTR6ACJIRC3BML3PV7UMQM.json","graph_json":"https://pith.science/api/pith-number/AHS5CTR6ACJIRC3BML3PV7UMQM/graph.json","events_json":"https://pith.science/api/pith-number/AHS5CTR6ACJIRC3BML3PV7UMQM/events.json","paper":"https://pith.science/paper/AHS5CTR6"},"agent_actions":{"view_html":"https://pith.science/pith/AHS5CTR6ACJIRC3BML3PV7UMQM","download_json":"https://pith.science/pith/AHS5CTR6ACJIRC3BML3PV7UMQM.json","view_paper":"https://pith.science/paper/AHS5CTR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23009&json=true","fetch_graph":"https://pith.science/api/pith-number/AHS5CTR6ACJIRC3BML3PV7UMQM/graph.json","fetch_events":"https://pith.science/api/pith-number/AHS5CTR6ACJIRC3BML3PV7UMQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHS5CTR6ACJIRC3BML3PV7UMQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHS5CTR6ACJIRC3BML3PV7UMQM/action/storage_attestation","attest_author":"https://pith.science/pith/AHS5CTR6ACJIRC3BML3PV7UMQM/action/author_attestation","sign_citation":"https://pith.science/pith/AHS5CTR6ACJIRC3BML3PV7UMQM/action/citation_signature","submit_replication":"https://pith.science/pith/AHS5CTR6ACJIRC3BML3PV7UMQM/action/replication_record"}},"created_at":"2026-07-05T11:12:11.841383+00:00","updated_at":"2026-07-05T11:12:11.841383+00:00"}