{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H6AIBS544NQ2ITJNJ3GGUXQPN7","short_pith_number":"pith:H6AIBS54","schema_version":"1.0","canonical_sha256":"3f8080cbbce361a44d2d4ecc6a5e0f6fdc06c6df5563821f28402029ed46e55c","source":{"kind":"arxiv","id":"2506.04013","version":1},"attestation_state":"computed","paper":{"title":"Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Waibel, Seymanur Akti, Tuan Nam Nguyen","submitted_at":"2025-06-04T14:42:12Z","abstract_excerpt":"Expressive voice conversion aims to transfer both speaker identity and expressive attributes from a target speech to a given source speech. In this work, we improve over a self-supervised, non-autoregressive framework with a conditional variational autoencoder, focusing on reducing source timbre leakage and improving linguistic-acoustic disentanglement for better style transfer. To minimize style leakage, we use multilingual discrete speech units for content representation and reinforce embeddings with augmentation-based similarity loss and mix-style layer normalization. To enhance expressivit"},"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":"2506.04013","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-06-04T14:42:12Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"8b73927b2cfc9b119211ce9c080b68f28f417938ad05db85a38a7aa2c1fe402e","abstract_canon_sha256":"4e4c7c4a6c919e7066ff1280f0fcf43ab9e24e23aae597e1e21c2cbc1b9e5591"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:55.367201Z","signature_b64":"vU3DasxJJq7Cp63AuSfDu5Frb4s/Gg/TiaWo2k2f++oNyjQIOt5SH/ZcsBqgyWuQql1kYl/LPmcUKr53NGYUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8080cbbce361a44d2d4ecc6a5e0f6fdc06c6df5563821f28402029ed46e55c","last_reissued_at":"2026-07-05T11:15:55.366311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:55.366311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Better Disentanglement in Non-Autoregressive Zero-Shot Expressive Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Waibel, Seymanur Akti, Tuan Nam Nguyen","submitted_at":"2025-06-04T14:42:12Z","abstract_excerpt":"Expressive voice conversion aims to transfer both speaker identity and expressive attributes from a target speech to a given source speech. In this work, we improve over a self-supervised, non-autoregressive framework with a conditional variational autoencoder, focusing on reducing source timbre leakage and improving linguistic-acoustic disentanglement for better style transfer. To minimize style leakage, we use multilingual discrete speech units for content representation and reinforce embeddings with augmentation-based similarity loss and mix-style layer normalization. To enhance expressivit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04013","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/2506.04013/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":"2506.04013","created_at":"2026-07-05T11:15:55.366764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04013v1","created_at":"2026-07-05T11:15:55.366764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04013","created_at":"2026-07-05T11:15:55.366764+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6AIBS544NQ2","created_at":"2026-07-05T11:15:55.366764+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6AIBS544NQ2ITJN","created_at":"2026-07-05T11:15:55.366764+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6AIBS54","created_at":"2026-07-05T11:15:55.366764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07240","citing_title":"KIT's Submission to Cross-Lingual Voice Cloning in IWSLT 2026","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03039","citing_title":"Mixed-Precision Information Bottlenecks for On-Device Trait-State Disentanglement in Bipolar Agitation Detection","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6AIBS544NQ2ITJNJ3GGUXQPN7","json":"https://pith.science/pith/H6AIBS544NQ2ITJNJ3GGUXQPN7.json","graph_json":"https://pith.science/api/pith-number/H6AIBS544NQ2ITJNJ3GGUXQPN7/graph.json","events_json":"https://pith.science/api/pith-number/H6AIBS544NQ2ITJNJ3GGUXQPN7/events.json","paper":"https://pith.science/paper/H6AIBS54"},"agent_actions":{"view_html":"https://pith.science/pith/H6AIBS544NQ2ITJNJ3GGUXQPN7","download_json":"https://pith.science/pith/H6AIBS544NQ2ITJNJ3GGUXQPN7.json","view_paper":"https://pith.science/paper/H6AIBS54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04013&json=true","fetch_graph":"https://pith.science/api/pith-number/H6AIBS544NQ2ITJNJ3GGUXQPN7/graph.json","fetch_events":"https://pith.science/api/pith-number/H6AIBS544NQ2ITJNJ3GGUXQPN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6AIBS544NQ2ITJNJ3GGUXQPN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6AIBS544NQ2ITJNJ3GGUXQPN7/action/storage_attestation","attest_author":"https://pith.science/pith/H6AIBS544NQ2ITJNJ3GGUXQPN7/action/author_attestation","sign_citation":"https://pith.science/pith/H6AIBS544NQ2ITJNJ3GGUXQPN7/action/citation_signature","submit_replication":"https://pith.science/pith/H6AIBS544NQ2ITJNJ3GGUXQPN7/action/replication_record"}},"created_at":"2026-07-05T11:15:55.366764+00:00","updated_at":"2026-07-05T11:15:55.366764+00:00"}