{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:E75A5APHC5KCBHSSP3SGDWH4CW","short_pith_number":"pith:E75A5APH","schema_version":"1.0","canonical_sha256":"27fa0e81e71754209e527ee461d8fc1584623ef2db4420dd8618a6acecc25cd2","source":{"kind":"arxiv","id":"2406.07846","version":1},"attestation_state":"computed","paper":{"title":"DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jixun Yao, Lei Xie, Mengxiao Bi, Pengcheng Zhu, Shuai Wang, Zhichao Wang, Ziqian Ning","submitted_at":"2024-06-12T03:25:18Z","abstract_excerpt":"Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms. Nonetheless, the recognition-synthesis framework hinders end-to-end optimization, and the instability of automatic speech recognition (ASR) model with short chunks makes it challenging to further reduce latency. To address these issues, we propose an end-to-end model, DualVC 3. With speaker-independent semantic tokens to guide the training of the content encoder, the "},"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":"2406.07846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T03:25:18Z","cross_cats_sorted":[],"title_canon_sha256":"5a6601f56015d01c1101bfe9239799b781079503266819d196143b77f3868937","abstract_canon_sha256":"7c1e2def69611df3408146abb878c9cc02d8fb618607f9ec52f19cf74f21a90b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:39.305215Z","signature_b64":"VJ65MYd9ckb+dPZeLFFCrWMp99V3Suc78XbRFBJQ8bFysb4YX/tsfrKpqdpd3iBf+X8HdUfKNV99fA83aNiSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27fa0e81e71754209e527ee461d8fc1584623ef2db4420dd8618a6acecc25cd2","last_reissued_at":"2026-07-05T08:30:39.304622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:39.304622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jixun Yao, Lei Xie, Mengxiao Bi, Pengcheng Zhu, Shuai Wang, Zhichao Wang, Ziqian Ning","submitted_at":"2024-06-12T03:25:18Z","abstract_excerpt":"Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms. Nonetheless, the recognition-synthesis framework hinders end-to-end optimization, and the instability of automatic speech recognition (ASR) model with short chunks makes it challenging to further reduce latency. To address these issues, we propose an end-to-end model, DualVC 3. With speaker-independent semantic tokens to guide the training of the content encoder, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07846","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/2406.07846/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":"2406.07846","created_at":"2026-07-05T08:30:39.304680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07846v1","created_at":"2026-07-05T08:30:39.304680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07846","created_at":"2026-07-05T08:30:39.304680+00:00"},{"alias_kind":"pith_short_12","alias_value":"E75A5APHC5KC","created_at":"2026-07-05T08:30:39.304680+00:00"},{"alias_kind":"pith_short_16","alias_value":"E75A5APHC5KCBHSS","created_at":"2026-07-05T08:30:39.304680+00:00"},{"alias_kind":"pith_short_8","alias_value":"E75A5APH","created_at":"2026-07-05T08:30:39.304680+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/E75A5APHC5KCBHSSP3SGDWH4CW","json":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW.json","graph_json":"https://pith.science/api/pith-number/E75A5APHC5KCBHSSP3SGDWH4CW/graph.json","events_json":"https://pith.science/api/pith-number/E75A5APHC5KCBHSSP3SGDWH4CW/events.json","paper":"https://pith.science/paper/E75A5APH"},"agent_actions":{"view_html":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW","download_json":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW.json","view_paper":"https://pith.science/paper/E75A5APH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07846&json=true","fetch_graph":"https://pith.science/api/pith-number/E75A5APHC5KCBHSSP3SGDWH4CW/graph.json","fetch_events":"https://pith.science/api/pith-number/E75A5APHC5KCBHSSP3SGDWH4CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW/action/storage_attestation","attest_author":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW/action/author_attestation","sign_citation":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW/action/citation_signature","submit_replication":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW/action/replication_record"}},"created_at":"2026-07-05T08:30:39.304680+00:00","updated_at":"2026-07-05T08:30:39.304680+00:00"}