{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3UINMD2BZKEBZMCX7PLMOZW64S","short_pith_number":"pith:3UINMD2B","schema_version":"1.0","canonical_sha256":"dd10d60f41ca881cb057fbd6c766dee483f8397e681ae12a45b3a92d4700e280","source":{"kind":"arxiv","id":"2112.04424","version":2},"attestation_state":"computed","paper":{"title":"Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dung Tran, Kazuhito Koishida, Peter Chin, Trung Dang","submitted_at":"2021-12-08T17:27:39Z","abstract_excerpt":"Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data. Recently, self-supervised learning of speech representation has been shown to produce useful linguistic units without using transcripts, which can be directly passed to a VC model. In this paper, we showed that high-quality audio samples can be achieved by using a length resampling decoder, which enables the VC model to work in conjunction with different linguistic feature extractors and vocoders without requiring th"},"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":"2112.04424","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-08T17:27:39Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"fca3bdc5aeb2da8573d325c4f4f7ed9154b5680ff9d9beffb80f95bbd7af650f","abstract_canon_sha256":"d7af14a92164fb036b8251306d8bba4e3630540cbae10dca911531f4bf79fb2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:04.686546Z","signature_b64":"cBXrgypqHvruY37BWFL9CZBv8cx3/evXQbLcaQ9/O1iVe+P4BPEiNMz8D2f7D5GHGULKxyC0ep1qzJSj3GzNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd10d60f41ca881cb057fbd6c766dee483f8397e681ae12a45b3a92d4700e280","last_reissued_at":"2026-07-05T03:56:04.686121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:04.686121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dung Tran, Kazuhito Koishida, Peter Chin, Trung Dang","submitted_at":"2021-12-08T17:27:39Z","abstract_excerpt":"Unsupervised Zero-Shot Voice Conversion (VC) aims to modify the speaker characteristic of an utterance to match an unseen target speaker without relying on parallel training data. Recently, self-supervised learning of speech representation has been shown to produce useful linguistic units without using transcripts, which can be directly passed to a VC model. In this paper, we showed that high-quality audio samples can be achieved by using a length resampling decoder, which enables the VC model to work in conjunction with different linguistic feature extractors and vocoders without requiring th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04424","kind":"arxiv","version":2},"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/2112.04424/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":"2112.04424","created_at":"2026-07-05T03:56:04.686175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04424v2","created_at":"2026-07-05T03:56:04.686175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04424","created_at":"2026-07-05T03:56:04.686175+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UINMD2BZKEB","created_at":"2026-07-05T03:56:04.686175+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UINMD2BZKEBZMCX","created_at":"2026-07-05T03:56:04.686175+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UINMD2B","created_at":"2026-07-05T03:56:04.686175+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/3UINMD2BZKEBZMCX7PLMOZW64S","json":"https://pith.science/pith/3UINMD2BZKEBZMCX7PLMOZW64S.json","graph_json":"https://pith.science/api/pith-number/3UINMD2BZKEBZMCX7PLMOZW64S/graph.json","events_json":"https://pith.science/api/pith-number/3UINMD2BZKEBZMCX7PLMOZW64S/events.json","paper":"https://pith.science/paper/3UINMD2B"},"agent_actions":{"view_html":"https://pith.science/pith/3UINMD2BZKEBZMCX7PLMOZW64S","download_json":"https://pith.science/pith/3UINMD2BZKEBZMCX7PLMOZW64S.json","view_paper":"https://pith.science/paper/3UINMD2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04424&json=true","fetch_graph":"https://pith.science/api/pith-number/3UINMD2BZKEBZMCX7PLMOZW64S/graph.json","fetch_events":"https://pith.science/api/pith-number/3UINMD2BZKEBZMCX7PLMOZW64S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UINMD2BZKEBZMCX7PLMOZW64S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UINMD2BZKEBZMCX7PLMOZW64S/action/storage_attestation","attest_author":"https://pith.science/pith/3UINMD2BZKEBZMCX7PLMOZW64S/action/author_attestation","sign_citation":"https://pith.science/pith/3UINMD2BZKEBZMCX7PLMOZW64S/action/citation_signature","submit_replication":"https://pith.science/pith/3UINMD2BZKEBZMCX7PLMOZW64S/action/replication_record"}},"created_at":"2026-07-05T03:56:04.686175+00:00","updated_at":"2026-07-05T03:56:04.686175+00:00"}