{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CJ2RWT5RNAS5GUVYCTNKQUPBQQ","short_pith_number":"pith:CJ2RWT5R","schema_version":"1.0","canonical_sha256":"12751b4fb16825d352b814daa851e18420d3d3b2f3f6114e5bd3ff9fe1d03792","source":{"kind":"arxiv","id":"2406.04494","version":1},"attestation_state":"computed","paper":{"title":"Towards Naturalistic Voice Conversion: NaturalVoices Dataset with an Automatic Processing Pipeline","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ali N. Salman, Berrak Sisman, Carlos Busso, Ismail Rasim Ulgen, Shreeram Suresh Chandra, Zongyang Du","submitted_at":"2024-06-06T20:38:19Z","abstract_excerpt":"Voice conversion (VC) research traditionally depends on scripted or acted speech, which lacks the natural spontaneity of real-life conversations. While natural speech data is limited for VC, our study focuses on filling in this gap. We introduce a novel data-sourcing pipeline that makes the release of a natural speech dataset for VC, named NaturalVoices. The pipeline extracts rich information in speech such as emotion and signal-to-noise ratio (SNR) from raw podcast data, utilizing recent deep learning methods and providing flexibility and ease of use. NaturalVoices marks a large-scale, sponta"},"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":"2406.04494","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-06T20:38:19Z","cross_cats_sorted":[],"title_canon_sha256":"196b5c83ed30a14b56fe8df785f525c90f251156dcdd0134355fbfb693faf65c","abstract_canon_sha256":"91350d5e0a4bf61112529458b3f288ac27f409e9db567d561b6adb5a57012f11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:44.525650Z","signature_b64":"blMeD4UonCTotaWYQTSU8GKqfkK08UvSh6NHYqv4VMNXq8Ozu6KW2Zjg/jOEUFYulkBmls3UIG/LBEdLbSeyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12751b4fb16825d352b814daa851e18420d3d3b2f3f6114e5bd3ff9fe1d03792","last_reissued_at":"2026-07-05T08:28:44.525212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:44.525212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Naturalistic Voice Conversion: NaturalVoices Dataset with an Automatic Processing Pipeline","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Ali N. Salman, Berrak Sisman, Carlos Busso, Ismail Rasim Ulgen, Shreeram Suresh Chandra, Zongyang Du","submitted_at":"2024-06-06T20:38:19Z","abstract_excerpt":"Voice conversion (VC) research traditionally depends on scripted or acted speech, which lacks the natural spontaneity of real-life conversations. While natural speech data is limited for VC, our study focuses on filling in this gap. We introduce a novel data-sourcing pipeline that makes the release of a natural speech dataset for VC, named NaturalVoices. The pipeline extracts rich information in speech such as emotion and signal-to-noise ratio (SNR) from raw podcast data, utilizing recent deep learning methods and providing flexibility and ease of use. NaturalVoices marks a large-scale, sponta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04494","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/2406.04494/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":"2406.04494","created_at":"2026-07-05T08:28:44.525267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04494v1","created_at":"2026-07-05T08:28:44.525267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04494","created_at":"2026-07-05T08:28:44.525267+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJ2RWT5RNAS5","created_at":"2026-07-05T08:28:44.525267+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJ2RWT5RNAS5GUVY","created_at":"2026-07-05T08:28:44.525267+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJ2RWT5R","created_at":"2026-07-05T08:28:44.525267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19534","citing_title":"Training-Free Multi-Step Audio Source Separation","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJ2RWT5RNAS5GUVYCTNKQUPBQQ","json":"https://pith.science/pith/CJ2RWT5RNAS5GUVYCTNKQUPBQQ.json","graph_json":"https://pith.science/api/pith-number/CJ2RWT5RNAS5GUVYCTNKQUPBQQ/graph.json","events_json":"https://pith.science/api/pith-number/CJ2RWT5RNAS5GUVYCTNKQUPBQQ/events.json","paper":"https://pith.science/paper/CJ2RWT5R"},"agent_actions":{"view_html":"https://pith.science/pith/CJ2RWT5RNAS5GUVYCTNKQUPBQQ","download_json":"https://pith.science/pith/CJ2RWT5RNAS5GUVYCTNKQUPBQQ.json","view_paper":"https://pith.science/paper/CJ2RWT5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04494&json=true","fetch_graph":"https://pith.science/api/pith-number/CJ2RWT5RNAS5GUVYCTNKQUPBQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CJ2RWT5RNAS5GUVYCTNKQUPBQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJ2RWT5RNAS5GUVYCTNKQUPBQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJ2RWT5RNAS5GUVYCTNKQUPBQQ/action/storage_attestation","attest_author":"https://pith.science/pith/CJ2RWT5RNAS5GUVYCTNKQUPBQQ/action/author_attestation","sign_citation":"https://pith.science/pith/CJ2RWT5RNAS5GUVYCTNKQUPBQQ/action/citation_signature","submit_replication":"https://pith.science/pith/CJ2RWT5RNAS5GUVYCTNKQUPBQQ/action/replication_record"}},"created_at":"2026-07-05T08:28:44.525267+00:00","updated_at":"2026-07-05T08:28:44.525267+00:00"}