{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XL622AROIDWAL7CCQZM5ONAOVS","short_pith_number":"pith:XL622ARO","schema_version":"1.0","canonical_sha256":"bafdad022e40ec05fc428659d7340eac842d769f31d49c8d1f18b695264997bd","source":{"kind":"arxiv","id":"2608.02235","version":1},"attestation_state":"computed","paper":{"title":"Domain-Specific Evaluation of Text-to-Speech Systems: A Multi-Metric Benchmarking Study","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Jafar, Amal Sarmad, Maryam Bashir, Shifa Yousaf","submitted_at":"2026-08-03T13:49:11Z","abstract_excerpt":"Recent advances in neural text-to-speech (TTS) systems have substantially improved speech naturalness and intelligibility across many languages. However, comprehensive evaluation methodologies that jointly assess perceptual quality, speaker similarity, and acoustic fidelity across diverse speech domains remain limited, particularly for low-resource and underrepresented languages. This paper presents a reproducible, multi-metric benchmarking framework for systematic evaluation of modern TTS systems through domain-specific analysis. The proposed framework integrates complementary subjective and "},"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":"2608.02235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-03T13:49:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d67303fb41ac83cde47ea94a28cedd677f268a824918e32a741b14ff12b49379","abstract_canon_sha256":"2c5e0f6e2f9fe3fee80521b112659a66e6d2bb8937fd9f86b5ef0b2eaa9c9b5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:11:27.979057Z","signature_b64":"0PlbZXLnDR3POEa34BCl9JTilh88IKkHzqGvFDQvn4FH/VhETRfeuCv6qtJDMgcxxv62Q0Zo9/uXObK3yo4DBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bafdad022e40ec05fc428659d7340eac842d769f31d49c8d1f18b695264997bd","last_reissued_at":"2026-08-04T02:11:27.977428Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:11:27.977428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Specific Evaluation of Text-to-Speech Systems: A Multi-Metric Benchmarking Study","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ali Jafar, Amal Sarmad, Maryam Bashir, Shifa Yousaf","submitted_at":"2026-08-03T13:49:11Z","abstract_excerpt":"Recent advances in neural text-to-speech (TTS) systems have substantially improved speech naturalness and intelligibility across many languages. However, comprehensive evaluation methodologies that jointly assess perceptual quality, speaker similarity, and acoustic fidelity across diverse speech domains remain limited, particularly for low-resource and underrepresented languages. This paper presents a reproducible, multi-metric benchmarking framework for systematic evaluation of modern TTS systems through domain-specific analysis. The proposed framework integrates complementary subjective and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02235","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/2608.02235/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":"2608.02235","created_at":"2026-08-04T02:11:27.979023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02235v1","created_at":"2026-08-04T02:11:27.979023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02235","created_at":"2026-08-04T02:11:27.979023+00:00"},{"alias_kind":"pith_short_12","alias_value":"XL622AROIDWA","created_at":"2026-08-04T02:11:27.979023+00:00"},{"alias_kind":"pith_short_16","alias_value":"XL622AROIDWAL7CC","created_at":"2026-08-04T02:11:27.979023+00:00"},{"alias_kind":"pith_short_8","alias_value":"XL622ARO","created_at":"2026-08-04T02:11:27.979023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XL622AROIDWAL7CCQZM5ONAOVS","json":"https://pith.science/pith/XL622AROIDWAL7CCQZM5ONAOVS.json","graph_json":"https://pith.science/api/pith-number/XL622AROIDWAL7CCQZM5ONAOVS/graph.json","events_json":"https://pith.science/api/pith-number/XL622AROIDWAL7CCQZM5ONAOVS/events.json","paper":"https://pith.science/paper/XL622ARO"},"agent_actions":{"view_html":"https://pith.science/pith/XL622AROIDWAL7CCQZM5ONAOVS","download_json":"https://pith.science/pith/XL622AROIDWAL7CCQZM5ONAOVS.json","view_paper":"https://pith.science/paper/XL622ARO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02235&json=true","fetch_graph":"https://pith.science/api/pith-number/XL622AROIDWAL7CCQZM5ONAOVS/graph.json","fetch_events":"https://pith.science/api/pith-number/XL622AROIDWAL7CCQZM5ONAOVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XL622AROIDWAL7CCQZM5ONAOVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XL622AROIDWAL7CCQZM5ONAOVS/action/storage_attestation","attest_author":"https://pith.science/pith/XL622AROIDWAL7CCQZM5ONAOVS/action/author_attestation","sign_citation":"https://pith.science/pith/XL622AROIDWAL7CCQZM5ONAOVS/action/citation_signature","submit_replication":"https://pith.science/pith/XL622AROIDWAL7CCQZM5ONAOVS/action/replication_record"}},"created_at":"2026-08-04T02:11:27.979023+00:00","updated_at":"2026-08-04T02:11:27.979023+00:00"}