{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X4TVX2KZFUEWUAMDT2Y3AY72YE","short_pith_number":"pith:X4TVX2KZ","schema_version":"1.0","canonical_sha256":"bf275be9592d096a01839eb1b063fac128a25b2da6ca1a3bbd7167fb65cedd87","source":{"kind":"arxiv","id":"2407.12707","version":3},"attestation_state":"computed","paper":{"title":"TTSDS -- Text-to-Speech Distribution Score","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Christoph Minixhofer, Ond\\v{r}ej Klejch, Peter Bell","submitted_at":"2024-07-17T16:30:27Z","abstract_excerpt":"Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose evaluating the quality of synthetic speech as a combination of multiple factors such as prosody, speaker identity, and intelligibility. Our approach assesses how well synthetic speech mirrors real speech by obtaining correlates of each factor and measuring their distance from both real speech datasets and noise datasets. We benchmark 35 TTS systems developed be"},"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":"2407.12707","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T16:30:27Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"f8bc0512143485ca6066323cbd516a93e018cc4840250c46cb1900dd1378b977","abstract_canon_sha256":"5345a3ceffd66ed74429e44142f04f99573f68e9fd04784376f7b3c56f0bd7e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:28.045991Z","signature_b64":"pYSU6yZKwlQC85x0bZBkxbb0S6ybEokUATOHEo11FWxCR1jWIEsGFgi12BW7sg2HE+QYSEQKkzW4zHQXmjqHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf275be9592d096a01839eb1b063fac128a25b2da6ca1a3bbd7167fb65cedd87","last_reissued_at":"2026-07-05T09:42:28.045501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:28.045501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TTSDS -- Text-to-Speech Distribution Score","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Christoph Minixhofer, Ond\\v{r}ej Klejch, Peter Bell","submitted_at":"2024-07-17T16:30:27Z","abstract_excerpt":"Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose evaluating the quality of synthetic speech as a combination of multiple factors such as prosody, speaker identity, and intelligibility. Our approach assesses how well synthetic speech mirrors real speech by obtaining correlates of each factor and measuring their distance from both real speech datasets and noise datasets. We benchmark 35 TTS systems developed be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12707","kind":"arxiv","version":3},"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/2407.12707/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":"2407.12707","created_at":"2026-07-05T09:42:28.045559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12707v3","created_at":"2026-07-05T09:42:28.045559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12707","created_at":"2026-07-05T09:42:28.045559+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4TVX2KZFUEW","created_at":"2026-07-05T09:42:28.045559+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4TVX2KZFUEWUAMD","created_at":"2026-07-05T09:42:28.045559+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4TVX2KZ","created_at":"2026-07-05T09:42:28.045559+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18323","citing_title":"Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE","json":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE.json","graph_json":"https://pith.science/api/pith-number/X4TVX2KZFUEWUAMDT2Y3AY72YE/graph.json","events_json":"https://pith.science/api/pith-number/X4TVX2KZFUEWUAMDT2Y3AY72YE/events.json","paper":"https://pith.science/paper/X4TVX2KZ"},"agent_actions":{"view_html":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE","download_json":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE.json","view_paper":"https://pith.science/paper/X4TVX2KZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12707&json=true","fetch_graph":"https://pith.science/api/pith-number/X4TVX2KZFUEWUAMDT2Y3AY72YE/graph.json","fetch_events":"https://pith.science/api/pith-number/X4TVX2KZFUEWUAMDT2Y3AY72YE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/action/storage_attestation","attest_author":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/action/author_attestation","sign_citation":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/action/citation_signature","submit_replication":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/action/replication_record"}},"created_at":"2026-07-05T09:42:28.045559+00:00","updated_at":"2026-07-05T09:42:28.045559+00:00"}