{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BJURRVDKGZVBQXBTUJ4GS72SV6","short_pith_number":"pith:BJURRVDK","schema_version":"1.0","canonical_sha256":"0a6918d46a366a185c33a278697f52afa33e2d1e42e5f3ea073d6e4ec54172ec","source":{"kind":"arxiv","id":"2606.09050","version":1},"attestation_state":"computed","paper":{"title":"MeanVC 2: Robust Low-Latency Streaming Zero-Shot Voice Conversion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dake Guo, Guobin Ma, Hanke Xie, Jingbin Hu, Lei Xie, Pengcheng Zhu, Yanbo Wang, Yuepeng Jiang, Yuxuan Xia","submitted_at":"2026-06-08T05:39:23Z","abstract_excerpt":"Streaming zero-shot voice conversion (VC) has become increasingly popular due to its potential for real-time applications. The recently proposed MeanVC achieves lightweight streaming zero-shot VC, but it has several limitations: its chunk-wise autoregressive denoising doubles the effective training sequence length, conversion quality degrades under small-chunk settings, and its timbre encoder directly relies on reference mel-spectrograms, making it sensitive to reference audio quality. To address these limitations we propose MeanVC 2. We introduce future-receptive chunking (FRC), which explici"},"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":"2606.09050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T05:39:23Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8b59a409271bdead971ef9c1595a2b45e0b5326bd1e3f880f1b08cbe1e8f3b0b","abstract_canon_sha256":"a8f8a051b1212d5bd73976f59455cb1b269aea8d7f473f1014827ed5f4870b02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:55.712636Z","signature_b64":"X8mOoIDPSPV/1d2p3+cIMC6XhE+X/m4o9/omq2ik2N40KaUXg2WEar/DKIr5IvpdTu3yg9moM9aCg6WOHFyhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a6918d46a366a185c33a278697f52afa33e2d1e42e5f3ea073d6e4ec54172ec","last_reissued_at":"2026-06-09T02:07:55.711766Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:55.711766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MeanVC 2: Robust Low-Latency Streaming Zero-Shot Voice Conversion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dake Guo, Guobin Ma, Hanke Xie, Jingbin Hu, Lei Xie, Pengcheng Zhu, Yanbo Wang, Yuepeng Jiang, Yuxuan Xia","submitted_at":"2026-06-08T05:39:23Z","abstract_excerpt":"Streaming zero-shot voice conversion (VC) has become increasingly popular due to its potential for real-time applications. The recently proposed MeanVC achieves lightweight streaming zero-shot VC, but it has several limitations: its chunk-wise autoregressive denoising doubles the effective training sequence length, conversion quality degrades under small-chunk settings, and its timbre encoder directly relies on reference mel-spectrograms, making it sensitive to reference audio quality. To address these limitations we propose MeanVC 2. We introduce future-receptive chunking (FRC), which explici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09050","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/2606.09050/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":"2606.09050","created_at":"2026-06-09T02:07:55.711900+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09050v1","created_at":"2026-06-09T02:07:55.711900+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09050","created_at":"2026-06-09T02:07:55.711900+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJURRVDKGZVB","created_at":"2026-06-09T02:07:55.711900+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJURRVDKGZVBQXBT","created_at":"2026-06-09T02:07:55.711900+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJURRVDK","created_at":"2026-06-09T02:07:55.711900+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/BJURRVDKGZVBQXBTUJ4GS72SV6","json":"https://pith.science/pith/BJURRVDKGZVBQXBTUJ4GS72SV6.json","graph_json":"https://pith.science/api/pith-number/BJURRVDKGZVBQXBTUJ4GS72SV6/graph.json","events_json":"https://pith.science/api/pith-number/BJURRVDKGZVBQXBTUJ4GS72SV6/events.json","paper":"https://pith.science/paper/BJURRVDK"},"agent_actions":{"view_html":"https://pith.science/pith/BJURRVDKGZVBQXBTUJ4GS72SV6","download_json":"https://pith.science/pith/BJURRVDKGZVBQXBTUJ4GS72SV6.json","view_paper":"https://pith.science/paper/BJURRVDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09050&json=true","fetch_graph":"https://pith.science/api/pith-number/BJURRVDKGZVBQXBTUJ4GS72SV6/graph.json","fetch_events":"https://pith.science/api/pith-number/BJURRVDKGZVBQXBTUJ4GS72SV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJURRVDKGZVBQXBTUJ4GS72SV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJURRVDKGZVBQXBTUJ4GS72SV6/action/storage_attestation","attest_author":"https://pith.science/pith/BJURRVDKGZVBQXBTUJ4GS72SV6/action/author_attestation","sign_citation":"https://pith.science/pith/BJURRVDKGZVBQXBTUJ4GS72SV6/action/citation_signature","submit_replication":"https://pith.science/pith/BJURRVDKGZVBQXBTUJ4GS72SV6/action/replication_record"}},"created_at":"2026-06-09T02:07:55.711900+00:00","updated_at":"2026-06-09T02:07:55.711900+00:00"}