{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:E75A5APHC5KCBHSSP3SGDWH4CW","short_pith_number":"pith:E75A5APH","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"},"canonical_sha256":"27fa0e81e71754209e527ee461d8fc1584623ef2db4420dd8618a6acecc25cd2","source":{"kind":"arxiv","id":"2406.07846","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07846","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07846v1","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07846","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_12","alias_value":"E75A5APHC5KC","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"E75A5APHC5KCBHSS","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"E75A5APH","created_at":"2026-07-05T08:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:E75A5APHC5KCBHSSP3SGDWH4CW","target":"record","payload":{"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"},"canonical_sha256":"27fa0e81e71754209e527ee461d8fc1584623ef2db4420dd8618a6acecc25cd2","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"},"source_kind":"arxiv","source_id":"2406.07846","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:30:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cxvIK3MgCnRHad2wAhC9emJBRAQBvb9SDGiLQaE7XvmnA4lkAi60KoL2cGzG+XQkMQ0CjWwDRLYbjXSH562aAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:13:23.411113Z"},"content_sha256":"ce37189aa6477ac036ecccf91d60fcc9e4167588743e49467fdb05fa74bb2860","schema_version":"1.0","event_id":"sha256:ce37189aa6477ac036ecccf91d60fcc9e4167588743e49467fdb05fa74bb2860"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:E75A5APHC5KCBHSSP3SGDWH4CW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:30:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPjOCe6Q/2KwlOE7zjKqCRTM+vJNWKPKVp8adaqS5HebsugpYnnYnJJLzHyb1DZIVNZjmq6BXcKeyxmRvkPJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:13:23.411720Z"},"content_sha256":"7902583f11ff5e5a37f71e020782d883cff382c9d26091fae0e2fd068a0947c2","schema_version":"1.0","event_id":"sha256:7902583f11ff5e5a37f71e020782d883cff382c9d26091fae0e2fd068a0947c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW/bundle.json","state_url":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E75A5APHC5KCBHSSP3SGDWH4CW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T10:13:23Z","links":{"resolver":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW","bundle":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW/bundle.json","state":"https://pith.science/pith/E75A5APHC5KCBHSSP3SGDWH4CW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E75A5APHC5KCBHSSP3SGDWH4CW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:E75A5APHC5KCBHSSP3SGDWH4CW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7c1e2def69611df3408146abb878c9cc02d8fb618607f9ec52f19cf74f21a90b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T03:25:18Z","title_canon_sha256":"5a6601f56015d01c1101bfe9239799b781079503266819d196143b77f3868937"},"schema_version":"1.0","source":{"id":"2406.07846","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07846","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07846v1","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07846","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_12","alias_value":"E75A5APHC5KC","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"E75A5APHC5KCBHSS","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"E75A5APH","created_at":"2026-07-05T08:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:7902583f11ff5e5a37f71e020782d883cff382c9d26091fae0e2fd068a0947c2","target":"graph","created_at":"2026-07-05T08:30:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.07846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jixun Yao, Lei Xie, Mengxiao Bi, Pengcheng Zhu, Shuai Wang, Zhichao Wang, Ziqian Ning","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T03:25:18Z","title":"DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07846","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ce37189aa6477ac036ecccf91d60fcc9e4167588743e49467fdb05fa74bb2860","target":"record","created_at":"2026-07-05T08:30:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7c1e2def69611df3408146abb878c9cc02d8fb618607f9ec52f19cf74f21a90b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-12T03:25:18Z","title_canon_sha256":"5a6601f56015d01c1101bfe9239799b781079503266819d196143b77f3868937"},"schema_version":"1.0","source":{"id":"2406.07846","kind":"arxiv","version":1}},"canonical_sha256":"27fa0e81e71754209e527ee461d8fc1584623ef2db4420dd8618a6acecc25cd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27fa0e81e71754209e527ee461d8fc1584623ef2db4420dd8618a6acecc25cd2","first_computed_at":"2026-07-05T08:30:39.304622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:39.304622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VJ65MYd9ckb+dPZeLFFCrWMp99V3Suc78XbRFBJQ8bFysb4YX/tsfrKpqdpd3iBf+X8HdUfKNV99fA83aNiSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:39.305215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07846","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce37189aa6477ac036ecccf91d60fcc9e4167588743e49467fdb05fa74bb2860","sha256:7902583f11ff5e5a37f71e020782d883cff382c9d26091fae0e2fd068a0947c2"],"state_sha256":"daa200ec38556fbe06fea47f658b902a9fd6ca8c83112694847a01d6e6ef3a2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZrGQir46mdJg2bdlC4pR3BZ4COYkR41ftOhnBK0MWlh2igiakAvOQT26GXiFzFlpuB8erKG+Gn0u2c+44c1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:13:23.417165Z","bundle_sha256":"d835ceb909204762276a54b1660dcf6140eefb444768766b161f85bccce595a4"}}