{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:T2R2XHBYLSFLLROTTJGCPD2LVS","short_pith_number":"pith:T2R2XHBY","schema_version":"1.0","canonical_sha256":"9ea3ab9c385c8ab5c5d39a4c278f4bac9618ffa1f43b9b7a60d47291be0ac129","source":{"kind":"arxiv","id":"2207.04356","version":1},"attestation_state":"computed","paper":{"title":"A Comparative Study of Self-supervised Speech Representation Based Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Shu-wen Yang, Tomoki Hayashi, Tomoki Toda, Wen-Chin Huang","submitted_at":"2022-07-10T01:02:22Z","abstract_excerpt":"We present a large-scale comparative study of self-supervised speech representation (S3R)-based voice conversion (VC). In the context of recognition-synthesis VC, S3Rs are attractive owing to their potential to replace expensive supervised representations such as phonetic posteriorgrams (PPGs), which are commonly adopted by state-of-the-art VC systems. Using S3PRL-VC, an open-source VC software we previously developed, we provide a series of in-depth objective and subjective analyses under three VC settings: intra-/cross-lingual any-to-one (A2O) and any-to-any (A2A) VC, using the voice convers"},"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":"2207.04356","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-07-10T01:02:22Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"a07bff7a61577197d868672a4575808dbcb32ea83b4012dfab51e41fd231c83c","abstract_canon_sha256":"cc5dc067fe06fb653f48941127540dedfdd45b2b14b8159ff48b33aba6496d63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:34.462135Z","signature_b64":"qvLY3l++ka0iwaIFpXYIYRBjts11+kumyxaqIjNQ4Ztno75S6RYZljq87VdOIjh+h1LEc6qSmYJwUCv3pnm8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ea3ab9c385c8ab5c5d39a4c278f4bac9618ffa1f43b9b7a60d47291be0ac129","last_reissued_at":"2026-07-05T05:18:34.461705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:34.461705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparative Study of Self-supervised Speech Representation Based Voice Conversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Shu-wen Yang, Tomoki Hayashi, Tomoki Toda, Wen-Chin Huang","submitted_at":"2022-07-10T01:02:22Z","abstract_excerpt":"We present a large-scale comparative study of self-supervised speech representation (S3R)-based voice conversion (VC). In the context of recognition-synthesis VC, S3Rs are attractive owing to their potential to replace expensive supervised representations such as phonetic posteriorgrams (PPGs), which are commonly adopted by state-of-the-art VC systems. Using S3PRL-VC, an open-source VC software we previously developed, we provide a series of in-depth objective and subjective analyses under three VC settings: intra-/cross-lingual any-to-one (A2O) and any-to-any (A2A) VC, using the voice convers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04356","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/2207.04356/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":"2207.04356","created_at":"2026-07-05T05:18:34.461758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04356v1","created_at":"2026-07-05T05:18:34.461758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04356","created_at":"2026-07-05T05:18:34.461758+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2R2XHBYLSFL","created_at":"2026-07-05T05:18:34.461758+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2R2XHBYLSFLLROT","created_at":"2026-07-05T05:18:34.461758+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2R2XHBY","created_at":"2026-07-05T05:18:34.461758+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/T2R2XHBYLSFLLROTTJGCPD2LVS","json":"https://pith.science/pith/T2R2XHBYLSFLLROTTJGCPD2LVS.json","graph_json":"https://pith.science/api/pith-number/T2R2XHBYLSFLLROTTJGCPD2LVS/graph.json","events_json":"https://pith.science/api/pith-number/T2R2XHBYLSFLLROTTJGCPD2LVS/events.json","paper":"https://pith.science/paper/T2R2XHBY"},"agent_actions":{"view_html":"https://pith.science/pith/T2R2XHBYLSFLLROTTJGCPD2LVS","download_json":"https://pith.science/pith/T2R2XHBYLSFLLROTTJGCPD2LVS.json","view_paper":"https://pith.science/paper/T2R2XHBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04356&json=true","fetch_graph":"https://pith.science/api/pith-number/T2R2XHBYLSFLLROTTJGCPD2LVS/graph.json","fetch_events":"https://pith.science/api/pith-number/T2R2XHBYLSFLLROTTJGCPD2LVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2R2XHBYLSFLLROTTJGCPD2LVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2R2XHBYLSFLLROTTJGCPD2LVS/action/storage_attestation","attest_author":"https://pith.science/pith/T2R2XHBYLSFLLROTTJGCPD2LVS/action/author_attestation","sign_citation":"https://pith.science/pith/T2R2XHBYLSFLLROTTJGCPD2LVS/action/citation_signature","submit_replication":"https://pith.science/pith/T2R2XHBYLSFLLROTTJGCPD2LVS/action/replication_record"}},"created_at":"2026-07-05T05:18:34.461758+00:00","updated_at":"2026-07-05T05:18:34.461758+00:00"}