{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3UINMD2BZKEBZMCX7PLMOZW64S","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":"d7af14a92164fb036b8251306d8bba4e3630540cbae10dca911531f4bf79fb2c","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-08T17:27:39Z","title_canon_sha256":"fca3bdc5aeb2da8573d325c4f4f7ed9154b5680ff9d9beffb80f95bbd7af650f"},"schema_version":"1.0","source":{"id":"2112.04424","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04424","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04424v2","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04424","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"3UINMD2BZKEB","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"3UINMD2BZKEBZMCX","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"3UINMD2B","created_at":"2026-07-05T03:56:04Z"}],"graph_snapshots":[{"event_id":"sha256:84587824e90485b3d3a1c6ca8784cf2db25c5e145c73f3fdddb91fc8602edf91","target":"graph","created_at":"2026-07-05T03:56:04Z","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/2112.04424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dung Tran, Kazuhito Koishida, Peter Chin, Trung Dang","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-08T17:27:39Z","title":"Training Robust Zero-Shot Voice Conversion Models with Self-supervised Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04424","kind":"arxiv","version":2},"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":"sha256:3d7a84f4fca440ca872b3eaeb164e013076395b8ed6688a616b3c0896fcdd5a1","target":"record","created_at":"2026-07-05T03:56:04Z","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":"d7af14a92164fb036b8251306d8bba4e3630540cbae10dca911531f4bf79fb2c","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2021-12-08T17:27:39Z","title_canon_sha256":"fca3bdc5aeb2da8573d325c4f4f7ed9154b5680ff9d9beffb80f95bbd7af650f"},"schema_version":"1.0","source":{"id":"2112.04424","kind":"arxiv","version":2}},"canonical_sha256":"dd10d60f41ca881cb057fbd6c766dee483f8397e681ae12a45b3a92d4700e280","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd10d60f41ca881cb057fbd6c766dee483f8397e681ae12a45b3a92d4700e280","first_computed_at":"2026-07-05T03:56:04.686121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:04.686121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cBXrgypqHvruY37BWFL9CZBv8cx3/evXQbLcaQ9/O1iVe+P4BPEiNMz8D2f7D5GHGULKxyC0ep1qzJSj3GzNBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:04.686546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04424","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d7a84f4fca440ca872b3eaeb164e013076395b8ed6688a616b3c0896fcdd5a1","sha256:84587824e90485b3d3a1c6ca8784cf2db25c5e145c73f3fdddb91fc8602edf91"],"state_sha256":"3f913682474ecdaa75b1e3a653904dd9db110473b883ee1774343bb43dc446b6"}