{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M3RNK4AQV3J53LFFVWVOJ6RSFR","short_pith_number":"pith:M3RNK4AQ","schema_version":"1.0","canonical_sha256":"66e2d57010aed3ddaca5adaae4fa322c495e1314f2dfa8a6ef0c8b882aa72e3c","source":{"kind":"arxiv","id":"2501.15613","version":1},"attestation_state":"computed","paper":{"title":"Stepback: Enhanced Disentanglement for Voice Conversion via Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Calbert Graham, Qian Yang","submitted_at":"2025-01-26T17:43:32Z","abstract_excerpt":"Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that rely on parallel data, our approach leverages deep learning techniques to enhance disentanglement completion and linguistic content preservation. The Stepback network incorporates a dual flow of different domain data inputs and uses constraints with self-destructive amendments to optimize the content encoder. Extensive experiments show that our model significa"},"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":"2501.15613","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-26T17:43:32Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"41288076ba7c8c7c9d68d918b813a49f6518915a6712ded2e5f867111051e630","abstract_canon_sha256":"02133edbe0dde2c5e8bf3a88efb0db54b5139fd88a3109b49eccd1bc0cee03dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:31.974310Z","signature_b64":"dGVjym2OAuxtVNa2WK+isQuZ1ljSy7iH5uByyOFHlODf9fPQTcUXX50kmIdcEaTmkz/zojzH91ouiqEDsnDfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e2d57010aed3ddaca5adaae4fa322c495e1314f2dfa8a6ef0c8b882aa72e3c","last_reissued_at":"2026-07-05T10:05:31.973818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:31.973818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stepback: Enhanced Disentanglement for Voice Conversion via Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Calbert Graham, Qian Yang","submitted_at":"2025-01-26T17:43:32Z","abstract_excerpt":"Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that rely on parallel data, our approach leverages deep learning techniques to enhance disentanglement completion and linguistic content preservation. The Stepback network incorporates a dual flow of different domain data inputs and uses constraints with self-destructive amendments to optimize the content encoder. Extensive experiments show that our model significa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15613","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/2501.15613/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":"2501.15613","created_at":"2026-07-05T10:05:31.973878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15613v1","created_at":"2026-07-05T10:05:31.973878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15613","created_at":"2026-07-05T10:05:31.973878+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3RNK4AQV3J5","created_at":"2026-07-05T10:05:31.973878+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3RNK4AQV3J53LFF","created_at":"2026-07-05T10:05:31.973878+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3RNK4AQ","created_at":"2026-07-05T10:05:31.973878+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15613","citing_title":"Stepback: Enhanced Disentanglement for Voice Conversion via Multi-Task Learning","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3RNK4AQV3J53LFFVWVOJ6RSFR","json":"https://pith.science/pith/M3RNK4AQV3J53LFFVWVOJ6RSFR.json","graph_json":"https://pith.science/api/pith-number/M3RNK4AQV3J53LFFVWVOJ6RSFR/graph.json","events_json":"https://pith.science/api/pith-number/M3RNK4AQV3J53LFFVWVOJ6RSFR/events.json","paper":"https://pith.science/paper/M3RNK4AQ"},"agent_actions":{"view_html":"https://pith.science/pith/M3RNK4AQV3J53LFFVWVOJ6RSFR","download_json":"https://pith.science/pith/M3RNK4AQV3J53LFFVWVOJ6RSFR.json","view_paper":"https://pith.science/paper/M3RNK4AQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15613&json=true","fetch_graph":"https://pith.science/api/pith-number/M3RNK4AQV3J53LFFVWVOJ6RSFR/graph.json","fetch_events":"https://pith.science/api/pith-number/M3RNK4AQV3J53LFFVWVOJ6RSFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3RNK4AQV3J53LFFVWVOJ6RSFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3RNK4AQV3J53LFFVWVOJ6RSFR/action/storage_attestation","attest_author":"https://pith.science/pith/M3RNK4AQV3J53LFFVWVOJ6RSFR/action/author_attestation","sign_citation":"https://pith.science/pith/M3RNK4AQV3J53LFFVWVOJ6RSFR/action/citation_signature","submit_replication":"https://pith.science/pith/M3RNK4AQV3J53LFFVWVOJ6RSFR/action/replication_record"}},"created_at":"2026-07-05T10:05:31.973878+00:00","updated_at":"2026-07-05T10:05:31.973878+00:00"}