{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KF3QR6E7PCISI5DB53QBVV2W6U","short_pith_number":"pith:KF3QR6E7","schema_version":"1.0","canonical_sha256":"517708f89f7891247461eee01ad756f51dd06b7c3f0f455109cacccbefa097a3","source":{"kind":"arxiv","id":"2506.16381","version":1},"attestation_state":"computed","paper":{"title":"InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenchen Yang, Dong Zhang, Kexin Huang, Liwei Fan, Qian Tu, Qinyuan Cheng, Shimin Li, Xipeng Qiu, Zhaoye Fei","submitted_at":"2025-06-19T15:08:01Z","abstract_excerpt":"In modern speech synthesis, paralinguistic information--such as a speaker's vocal timbre, emotional state, and dynamic prosody--plays a critical role in conveying nuance beyond mere semantics. Traditional Text-to-Speech (TTS) systems rely on fixed style labels or inserting a speech prompt to control these cues, which severely limits flexibility. Recent attempts seek to employ natural-language instructions to modulate paralinguistic features, substantially improving the generalization of instruction-driven TTS models. Although many TTS systems now support customized synthesis via textual descri"},"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":"2506.16381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T15:08:01Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3db0eb5b6ec43e419f4398a89e8acc4aa1121e7a3a7054d09c398d258392edd3","abstract_canon_sha256":"82169052f331a48a9c2d7f90eabf0739d3ceb0e1e325135fc39b79909058f0a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:35.532611Z","signature_b64":"ZwHTqi+6novCWDd9XXRNksNJ3n89kuzQP4KeNnCTcOjP/shJ9ksQdGdTLW2f9oNdUif+1hzJk+nMLytx5frNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"517708f89f7891247461eee01ad756f51dd06b7c3f0f455109cacccbefa097a3","last_reissued_at":"2026-07-05T11:24:35.532068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:35.532068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenchen Yang, Dong Zhang, Kexin Huang, Liwei Fan, Qian Tu, Qinyuan Cheng, Shimin Li, Xipeng Qiu, Zhaoye Fei","submitted_at":"2025-06-19T15:08:01Z","abstract_excerpt":"In modern speech synthesis, paralinguistic information--such as a speaker's vocal timbre, emotional state, and dynamic prosody--plays a critical role in conveying nuance beyond mere semantics. Traditional Text-to-Speech (TTS) systems rely on fixed style labels or inserting a speech prompt to control these cues, which severely limits flexibility. Recent attempts seek to employ natural-language instructions to modulate paralinguistic features, substantially improving the generalization of instruction-driven TTS models. Although many TTS systems now support customized synthesis via textual descri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16381","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/2506.16381/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":"2506.16381","created_at":"2026-07-05T11:24:35.532134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16381v1","created_at":"2026-07-05T11:24:35.532134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16381","created_at":"2026-07-05T11:24:35.532134+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF3QR6E7PCIS","created_at":"2026-07-05T11:24:35.532134+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF3QR6E7PCISI5DB","created_at":"2026-07-05T11:24:35.532134+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF3QR6E7","created_at":"2026-07-05T11:24:35.532134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24648","citing_title":"ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31729","citing_title":"Is Natural Always Appropriate? Investigating Naturalness and Appropriateness Across Different Domains for TTS Evaluation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17583","citing_title":"AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2601.15621","citing_title":"Qwen3-TTS Technical Report","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08363","citing_title":"CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16211","citing_title":"NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations","ref_index":18,"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":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U","json":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U.json","graph_json":"https://pith.science/api/pith-number/KF3QR6E7PCISI5DB53QBVV2W6U/graph.json","events_json":"https://pith.science/api/pith-number/KF3QR6E7PCISI5DB53QBVV2W6U/events.json","paper":"https://pith.science/paper/KF3QR6E7"},"agent_actions":{"view_html":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U","download_json":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U.json","view_paper":"https://pith.science/paper/KF3QR6E7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16381&json=true","fetch_graph":"https://pith.science/api/pith-number/KF3QR6E7PCISI5DB53QBVV2W6U/graph.json","fetch_events":"https://pith.science/api/pith-number/KF3QR6E7PCISI5DB53QBVV2W6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U/action/storage_attestation","attest_author":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U/action/author_attestation","sign_citation":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U/action/citation_signature","submit_replication":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U/action/replication_record"}},"created_at":"2026-07-05T11:24:35.532134+00:00","updated_at":"2026-07-05T11:24:35.532134+00:00"}