{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WHWC3CEIBVM3AXKOEHITVGT7PZ","short_pith_number":"pith:WHWC3CEI","canonical_record":{"source":{"id":"2402.16380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-26T07:58:33Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7e224fabcf4f938c7613aaa4cb3bec214a67ffa2dff230f65296c85282aa4a6b","abstract_canon_sha256":"76141b34f5b8754fe09a46218e0cfbeba1aa4e0befed7d8046402f0db7598cac"},"schema_version":"1.0"},"canonical_sha256":"b1ec2d88880d59b05d4e21d13a9a7f7e73b8de3c9c8e3c4b3f1fe2464d6e564b","source":{"kind":"arxiv","id":"2402.16380","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16380","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16380v1","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16380","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"WHWC3CEIBVM3","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"WHWC3CEIBVM3AXKO","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"WHWC3CEI","created_at":"2026-07-05T07:49:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WHWC3CEIBVM3AXKOEHITVGT7PZ","target":"record","payload":{"canonical_record":{"source":{"id":"2402.16380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-26T07:58:33Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7e224fabcf4f938c7613aaa4cb3bec214a67ffa2dff230f65296c85282aa4a6b","abstract_canon_sha256":"76141b34f5b8754fe09a46218e0cfbeba1aa4e0befed7d8046402f0db7598cac"},"schema_version":"1.0"},"canonical_sha256":"b1ec2d88880d59b05d4e21d13a9a7f7e73b8de3c9c8e3c4b3f1fe2464d6e564b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:20.843623Z","signature_b64":"E6sDFqXiJGD4aRqE5XafnzgwvwNYqsqRReHDkrbIlsjCKQweqQz1egNTS+aewg5zTyVVnEVbthJ7gcJFtSQwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1ec2d88880d59b05d4e21d13a9a7f7e73b8de3c9c8e3c4b3f1fe2464d6e564b","last_reissued_at":"2026-07-05T07:49:20.843198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:20.843198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.16380","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IDhLpD17DBuJkJFhlO4TsnbqPi+L0I7g0RroHxigV980/xevcwajpLI3IV4MhbcIZjMREIRtZyNJg1cb/QQlDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:47:41.773017Z"},"content_sha256":"7a7bb4b3753cc781917b24a204e7764c4bc769198a2753aadb48e5fa89ea023c","schema_version":"1.0","event_id":"sha256:7a7bb4b3753cc781917b24a204e7764c4bc769198a2753aadb48e5fa89ea023c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WHWC3CEIBVM3AXKOEHITVGT7PZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Automated End-to-End Open-Source Software for High-Quality Text-to-Speech Dataset Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Ahmet Gunduz, Fabio Minazzi, Golara Javadi, Kamer Ali Yuksel, Kareem Darwish, Nicola Sobieski, Sebastien Bratieres","submitted_at":"2024-02-26T07:58:33Z","abstract_excerpt":"Data availability is crucial for advancing artificial intelligence applications, including voice-based technologies. As content creation, particularly in social media, experiences increasing demand, translation and text-to-speech (TTS) technologies have become essential tools. Notably, the performance of these TTS technologies is highly dependent on the quality of the training data, emphasizing the mutual dependence of data availability and technological progress. This paper introduces an end-to-end tool to generate high-quality datasets for text-to-speech (TTS) models to address this critical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16380","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/2402.16380/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qhcymojTevw12JpBW8EsF7RYriNrA6OondLZyNStA7CJGspmCkpC5TZV357wNpHOFvlfrbiuc/K74VmUzYLKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:47:41.773408Z"},"content_sha256":"1de233b0b441113eaee227f92fb70a594e508cbe2d066fec9fa8d3d95eb8ff37","schema_version":"1.0","event_id":"sha256:1de233b0b441113eaee227f92fb70a594e508cbe2d066fec9fa8d3d95eb8ff37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WHWC3CEIBVM3AXKOEHITVGT7PZ/bundle.json","state_url":"https://pith.science/pith/WHWC3CEIBVM3AXKOEHITVGT7PZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WHWC3CEIBVM3AXKOEHITVGT7PZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T02:47:41Z","links":{"resolver":"https://pith.science/pith/WHWC3CEIBVM3AXKOEHITVGT7PZ","bundle":"https://pith.science/pith/WHWC3CEIBVM3AXKOEHITVGT7PZ/bundle.json","state":"https://pith.science/pith/WHWC3CEIBVM3AXKOEHITVGT7PZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WHWC3CEIBVM3AXKOEHITVGT7PZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WHWC3CEIBVM3AXKOEHITVGT7PZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"76141b34f5b8754fe09a46218e0cfbeba1aa4e0befed7d8046402f0db7598cac","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-26T07:58:33Z","title_canon_sha256":"7e224fabcf4f938c7613aaa4cb3bec214a67ffa2dff230f65296c85282aa4a6b"},"schema_version":"1.0","source":{"id":"2402.16380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16380","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16380v1","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16380","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"WHWC3CEIBVM3","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"WHWC3CEIBVM3AXKO","created_at":"2026-07-05T07:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"WHWC3CEI","created_at":"2026-07-05T07:49:20Z"}],"graph_snapshots":[{"event_id":"sha256:1de233b0b441113eaee227f92fb70a594e508cbe2d066fec9fa8d3d95eb8ff37","target":"graph","created_at":"2026-07-05T07:49:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.16380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data availability is crucial for advancing artificial intelligence applications, including voice-based technologies. As content creation, particularly in social media, experiences increasing demand, translation and text-to-speech (TTS) technologies have become essential tools. Notably, the performance of these TTS technologies is highly dependent on the quality of the training data, emphasizing the mutual dependence of data availability and technological progress. This paper introduces an end-to-end tool to generate high-quality datasets for text-to-speech (TTS) models to address this critical","authors_text":"Ahmet Gunduz, Fabio Minazzi, Golara Javadi, Kamer Ali Yuksel, Kareem Darwish, Nicola Sobieski, Sebastien Bratieres","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-26T07:58:33Z","title":"An Automated End-to-End Open-Source Software for High-Quality Text-to-Speech Dataset Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16380","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7a7bb4b3753cc781917b24a204e7764c4bc769198a2753aadb48e5fa89ea023c","target":"record","created_at":"2026-07-05T07:49:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"76141b34f5b8754fe09a46218e0cfbeba1aa4e0befed7d8046402f0db7598cac","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-26T07:58:33Z","title_canon_sha256":"7e224fabcf4f938c7613aaa4cb3bec214a67ffa2dff230f65296c85282aa4a6b"},"schema_version":"1.0","source":{"id":"2402.16380","kind":"arxiv","version":1}},"canonical_sha256":"b1ec2d88880d59b05d4e21d13a9a7f7e73b8de3c9c8e3c4b3f1fe2464d6e564b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1ec2d88880d59b05d4e21d13a9a7f7e73b8de3c9c8e3c4b3f1fe2464d6e564b","first_computed_at":"2026-07-05T07:49:20.843198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:20.843198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E6sDFqXiJGD4aRqE5XafnzgwvwNYqsqRReHDkrbIlsjCKQweqQz1egNTS+aewg5zTyVVnEVbthJ7gcJFtSQwDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:20.843623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a7bb4b3753cc781917b24a204e7764c4bc769198a2753aadb48e5fa89ea023c","sha256:1de233b0b441113eaee227f92fb70a594e508cbe2d066fec9fa8d3d95eb8ff37"],"state_sha256":"39d1f25b4113ce426184ce560792ced5d0aeb9519a106d8e6adf435b8981f7a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ddZZgodeI3dUQGTlsIDKY6QKB4ZBXPot5tiVLSM/+T21mQmDLX8a2UM+WBFhnAZ+t5VV4e0kcTU5Erlvn99mAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:47:41.775588Z","bundle_sha256":"383e43d88139b8e5d3de9c6281c76c8c253710576266d66e074898209cae03e5"}}