{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OY6D5LBZWSTUNZMQDCQ3DCLU3O","short_pith_number":"pith:OY6D5LBZ","schema_version":"1.0","canonical_sha256":"763c3eac39b4a746e59018a1b18974dbbb4762a5b7b94fd47f62181d4a246924","source":{"kind":"arxiv","id":"2410.13357","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Crowdsourced Audio for Text-to-Speech Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alex Peir\\'o-Lilja, Baybars K\\\"ulebi, Carme Armentano-Oller, Gerard Sant, Jos\\'e Giraldo, Mart\\'i Llopart-Font","submitted_at":"2024-10-17T09:07:57Z","abstract_excerpt":"High-quality audio data is a critical prerequisite for training robust text-to-speech models, which often limits the use of opportunistic or crowdsourced datasets. This paper presents an approach to overcome this limitation by implementing a denoising pipeline on the Catalan subset of Commonvoice, a crowd-sourced corpus known for its inherent noise and variability. The pipeline incorporates an audio enhancement phase followed by a selective filtering strategy. We developed an automatic filtering mechanism leveraging Non-Intrusive Speech Quality Assessment (NISQA) models to identify and retain "},"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":"2410.13357","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-17T09:07:57Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"eb18b94528768c4c2a85fa9c0d2abf7b1d2b04f79b94615433e03ebe4eac9cb6","abstract_canon_sha256":"ae7b8bf6771109cebbe24ddf769b690155e477ade441c7c2cf971c624f2761f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:59.363284Z","signature_b64":"TFZXnJe2C6K5g9z0ubWjuFkAofn4syLGqqzpAKMgmckkE6lwmnM6xiNvfS0aWxbQX1Zpz3Nw23pZ1BZAtgzfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"763c3eac39b4a746e59018a1b18974dbbb4762a5b7b94fd47f62181d4a246924","last_reissued_at":"2026-07-05T09:21:59.362750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:59.362750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Crowdsourced Audio for Text-to-Speech Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alex Peir\\'o-Lilja, Baybars K\\\"ulebi, Carme Armentano-Oller, Gerard Sant, Jos\\'e Giraldo, Mart\\'i Llopart-Font","submitted_at":"2024-10-17T09:07:57Z","abstract_excerpt":"High-quality audio data is a critical prerequisite for training robust text-to-speech models, which often limits the use of opportunistic or crowdsourced datasets. This paper presents an approach to overcome this limitation by implementing a denoising pipeline on the Catalan subset of Commonvoice, a crowd-sourced corpus known for its inherent noise and variability. The pipeline incorporates an audio enhancement phase followed by a selective filtering strategy. We developed an automatic filtering mechanism leveraging Non-Intrusive Speech Quality Assessment (NISQA) models to identify and retain "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13357","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/2410.13357/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":"2410.13357","created_at":"2026-07-05T09:21:59.362811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13357v1","created_at":"2026-07-05T09:21:59.362811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13357","created_at":"2026-07-05T09:21:59.362811+00:00"},{"alias_kind":"pith_short_12","alias_value":"OY6D5LBZWSTU","created_at":"2026-07-05T09:21:59.362811+00:00"},{"alias_kind":"pith_short_16","alias_value":"OY6D5LBZWSTUNZMQ","created_at":"2026-07-05T09:21:59.362811+00:00"},{"alias_kind":"pith_short_8","alias_value":"OY6D5LBZ","created_at":"2026-07-05T09:21:59.362811+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/OY6D5LBZWSTUNZMQDCQ3DCLU3O","json":"https://pith.science/pith/OY6D5LBZWSTUNZMQDCQ3DCLU3O.json","graph_json":"https://pith.science/api/pith-number/OY6D5LBZWSTUNZMQDCQ3DCLU3O/graph.json","events_json":"https://pith.science/api/pith-number/OY6D5LBZWSTUNZMQDCQ3DCLU3O/events.json","paper":"https://pith.science/paper/OY6D5LBZ"},"agent_actions":{"view_html":"https://pith.science/pith/OY6D5LBZWSTUNZMQDCQ3DCLU3O","download_json":"https://pith.science/pith/OY6D5LBZWSTUNZMQDCQ3DCLU3O.json","view_paper":"https://pith.science/paper/OY6D5LBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13357&json=true","fetch_graph":"https://pith.science/api/pith-number/OY6D5LBZWSTUNZMQDCQ3DCLU3O/graph.json","fetch_events":"https://pith.science/api/pith-number/OY6D5LBZWSTUNZMQDCQ3DCLU3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OY6D5LBZWSTUNZMQDCQ3DCLU3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OY6D5LBZWSTUNZMQDCQ3DCLU3O/action/storage_attestation","attest_author":"https://pith.science/pith/OY6D5LBZWSTUNZMQDCQ3DCLU3O/action/author_attestation","sign_citation":"https://pith.science/pith/OY6D5LBZWSTUNZMQDCQ3DCLU3O/action/citation_signature","submit_replication":"https://pith.science/pith/OY6D5LBZWSTUNZMQDCQ3DCLU3O/action/replication_record"}},"created_at":"2026-07-05T09:21:59.362811+00:00","updated_at":"2026-07-05T09:21:59.362811+00:00"}