{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QRRBDDM24RHE3XS76WYO2QTLWA","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":"52d9f32c2e1b09205ecf767466cb15769e0e468abc5fb5adc9bb00c14f374872","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-16T03:40:13Z","title_canon_sha256":"b31a6f8f6dfaa1bb04b1f282f1d6638bbfaccb6fea4a4b737f733dea684757cc"},"schema_version":"1.0","source":{"id":"2401.08096","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08096","created_at":"2026-07-05T07:34:55Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08096v2","created_at":"2026-07-05T07:34:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08096","created_at":"2026-07-05T07:34:55Z"},{"alias_kind":"pith_short_12","alias_value":"QRRBDDM24RHE","created_at":"2026-07-05T07:34:55Z"},{"alias_kind":"pith_short_16","alias_value":"QRRBDDM24RHE3XS7","created_at":"2026-07-05T07:34:55Z"},{"alias_kind":"pith_short_8","alias_value":"QRRBDDM2","created_at":"2026-07-05T07:34:55Z"}],"graph_snapshots":[{"event_id":"sha256:9c4af32b2381e11c2a117d66a36f10ee0a2d713cc4ff559d3ad71627021c2941","target":"graph","created_at":"2026-07-05T07:34:55Z","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/2401.08096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio has the potential ability to well represent content. Besides, the speaker-style modeling with pre-trained models making the process more complex. To tackle these issues, we introduce a new method named \"CTVC\" which utilizes disentangled speech representations with contrastive learning and time-invariant retrieval. Specifically, a similarity-based compression m","authors_text":"Huaizhen Tang, Jianzong Wang, Jing Xiao, Ning Cheng, Xulong Zhang, Yimin Deng","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-16T03:40:13Z","title":"Learning Disentangled Speech Representations with Contrastive Learning and Time-Invariant Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08096","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":"sha256:90585489938f31861f6bcc3667ff5c38d90ad7937f66baa2a2013b050e0ccdc2","target":"record","created_at":"2026-07-05T07:34:55Z","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":"52d9f32c2e1b09205ecf767466cb15769e0e468abc5fb5adc9bb00c14f374872","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-16T03:40:13Z","title_canon_sha256":"b31a6f8f6dfaa1bb04b1f282f1d6638bbfaccb6fea4a4b737f733dea684757cc"},"schema_version":"1.0","source":{"id":"2401.08096","kind":"arxiv","version":2}},"canonical_sha256":"8462118d9ae44e4dde5ff5b0ed426bb0023830083450109ff3b521808065b6bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8462118d9ae44e4dde5ff5b0ed426bb0023830083450109ff3b521808065b6bb","first_computed_at":"2026-07-05T07:34:55.349013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:55.349013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NcpvRhLfO3BE6ty3sh+OfOPl3JERqZWrTTjg8+wZcl2WvQhiwbIQuHiMIcEyBWrNAJtsr0ckzMLKrEMQDx0RAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:55.349671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08096","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90585489938f31861f6bcc3667ff5c38d90ad7937f66baa2a2013b050e0ccdc2","sha256:9c4af32b2381e11c2a117d66a36f10ee0a2d713cc4ff559d3ad71627021c2941"],"state_sha256":"31187fc872cd67d7bbe2ad86882a03c672b545231c5f4e4f21e590e1315b7ddb"}