{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SXARY6L5GV75PKMSTPAUCAS6PU","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":"b2c827ca9be93c37dd882079030cb0ab68f9223792713f54afe749cb5945021f","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-01T09:20:33Z","title_canon_sha256":"5792ebaae7ef06ecf157e33ba3a28c4ee3fc7e350ac56980171586a5d994c2bf"},"schema_version":"1.0","source":{"id":"2104.00355","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00355","created_at":"2026-07-05T03:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00355v3","created_at":"2026-07-05T03:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00355","created_at":"2026-07-05T03:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"SXARY6L5GV75","created_at":"2026-07-05T03:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"SXARY6L5GV75PKMS","created_at":"2026-07-05T03:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"SXARY6L5","created_at":"2026-07-05T03:00:52Z"}],"graph_snapshots":[{"event_id":"sha256:405fd8c03d5cd497e13b8085d0c0e5a2d991950eb02424ff616f059bd9f39302","target":"graph","created_at":"2026-07-05T03:00:52Z","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/2104.00355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker identity. This allows to synthesize speech in a controllable manner. We analyze various state-of-the-art, self-supervised representation learning methods and shed light on the advantages of each method while considering reconstruction quality and disentanglement properties. Specifically, we evaluate the F0 reconstruction, speaker identification performance (f","authors_text":"Abdelrahman Mohamed, Adam Polyak, Emmanuel Dupoux, Eugene Kharitonov, Jade Copet, Kushal Lakhotia, Wei-Ning Hsu, Yossi Adi","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-01T09:20:33Z","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00355","kind":"arxiv","version":3},"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":"sha256:8442cad14a9698fda9b6f1b731b4a262943c4d202c51d871c86dc4a38ee216fe","target":"record","created_at":"2026-07-05T03:00:52Z","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":"b2c827ca9be93c37dd882079030cb0ab68f9223792713f54afe749cb5945021f","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-04-01T09:20:33Z","title_canon_sha256":"5792ebaae7ef06ecf157e33ba3a28c4ee3fc7e350ac56980171586a5d994c2bf"},"schema_version":"1.0","source":{"id":"2104.00355","kind":"arxiv","version":3}},"canonical_sha256":"95c11c797d357fd7a9929bc141025e7d10b000eb416f473cc960fff29e9c746d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95c11c797d357fd7a9929bc141025e7d10b000eb416f473cc960fff29e9c746d","first_computed_at":"2026-07-05T03:00:52.070753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:00:52.070753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0XguFfM4DxVtktT+0SATwnbKYCGZVxIr5/8gLTuIURoaBUv5wBkmNf/SKYEgnnTRvsy9eUttXbV352pqbWPcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:00:52.071168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00355","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8442cad14a9698fda9b6f1b731b4a262943c4d202c51d871c86dc4a38ee216fe","sha256:405fd8c03d5cd497e13b8085d0c0e5a2d991950eb02424ff616f059bd9f39302"],"state_sha256":"c8742503f59bacd3d6dd2bbce9523f2b0b464fa46acb28f7a4d4d92e58553ff7"}