{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:675DJ6IKGAVYFN5DSX7KBYZBF7","short_pith_number":"pith:675DJ6IK","schema_version":"1.0","canonical_sha256":"f7fa34f90a302b82b7a395fea0e3212ff0292e8db36724288a992f82b32ac5fb","source":{"kind":"arxiv","id":"2606.08843","version":1},"attestation_state":"computed","paper":{"title":"From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Moshe Mandel, Shlomo E. Chazan","submitted_at":"2026-06-07T21:25:14Z","abstract_excerpt":"We present a voice conversion (VC) framework that utilizes K-Nearest Neighbors (KNN) retrieval over WavLM representations to align non-parallel source and target speech, constructing synthetic training pairs for supervised learning. The retrieved segments serve as synthetic inputs, while real target audio provides ground-truth outputs, forming a synthetic-to-real training paradigm that naturally supports multilingual data without requiring parallel corpora or explicit alignment. To ensure consistent target-speaker identity, we incorporate a speaker loss derived from a pretrained speaker verifi"},"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":"2606.08843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-07T21:25:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3379679814e84364ff6978e0c31379a297d9595e4a870d6b3942c1110c18211d","abstract_canon_sha256":"ccee64603bce7ce042630110e334709596ac3464903ef1d6fdc7c28721185463"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:42.430513Z","signature_b64":"ZyJ86JT0U/bp8l6YjNYYdpFzt+aIUrU6n8j2ZK4bvpV+uKOXUwsNUnidmuRa7/3+yymsBDQ12CjzP0/p+PXpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7fa34f90a302b82b7a395fea0e3212ff0292e8db36724288a992f82b32ac5fb","last_reissued_at":"2026-06-09T02:07:42.429658Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:42.429658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Moshe Mandel, Shlomo E. Chazan","submitted_at":"2026-06-07T21:25:14Z","abstract_excerpt":"We present a voice conversion (VC) framework that utilizes K-Nearest Neighbors (KNN) retrieval over WavLM representations to align non-parallel source and target speech, constructing synthetic training pairs for supervised learning. The retrieved segments serve as synthetic inputs, while real target audio provides ground-truth outputs, forming a synthetic-to-real training paradigm that naturally supports multilingual data without requiring parallel corpora or explicit alignment. To ensure consistent target-speaker identity, we incorporate a speaker loss derived from a pretrained speaker verifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08843","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/2606.08843/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":"2606.08843","created_at":"2026-06-09T02:07:42.429793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08843v1","created_at":"2026-06-09T02:07:42.429793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08843","created_at":"2026-06-09T02:07:42.429793+00:00"},{"alias_kind":"pith_short_12","alias_value":"675DJ6IKGAVY","created_at":"2026-06-09T02:07:42.429793+00:00"},{"alias_kind":"pith_short_16","alias_value":"675DJ6IKGAVYFN5D","created_at":"2026-06-09T02:07:42.429793+00:00"},{"alias_kind":"pith_short_8","alias_value":"675DJ6IK","created_at":"2026-06-09T02:07:42.429793+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/675DJ6IKGAVYFN5DSX7KBYZBF7","json":"https://pith.science/pith/675DJ6IKGAVYFN5DSX7KBYZBF7.json","graph_json":"https://pith.science/api/pith-number/675DJ6IKGAVYFN5DSX7KBYZBF7/graph.json","events_json":"https://pith.science/api/pith-number/675DJ6IKGAVYFN5DSX7KBYZBF7/events.json","paper":"https://pith.science/paper/675DJ6IK"},"agent_actions":{"view_html":"https://pith.science/pith/675DJ6IKGAVYFN5DSX7KBYZBF7","download_json":"https://pith.science/pith/675DJ6IKGAVYFN5DSX7KBYZBF7.json","view_paper":"https://pith.science/paper/675DJ6IK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08843&json=true","fetch_graph":"https://pith.science/api/pith-number/675DJ6IKGAVYFN5DSX7KBYZBF7/graph.json","fetch_events":"https://pith.science/api/pith-number/675DJ6IKGAVYFN5DSX7KBYZBF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/675DJ6IKGAVYFN5DSX7KBYZBF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/675DJ6IKGAVYFN5DSX7KBYZBF7/action/storage_attestation","attest_author":"https://pith.science/pith/675DJ6IKGAVYFN5DSX7KBYZBF7/action/author_attestation","sign_citation":"https://pith.science/pith/675DJ6IKGAVYFN5DSX7KBYZBF7/action/citation_signature","submit_replication":"https://pith.science/pith/675DJ6IKGAVYFN5DSX7KBYZBF7/action/replication_record"}},"created_at":"2026-06-09T02:07:42.429793+00:00","updated_at":"2026-06-09T02:07:42.429793+00:00"}