{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SO7A4TZXSBAL6EGVGW7VYNULWS","short_pith_number":"pith:SO7A4TZX","canonical_record":{"source":{"id":"2405.00930","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-02T01:11:15Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0498907ede3777956458b07b8937bfa5f476117b12a0919e2632bd7095026cdb","abstract_canon_sha256":"0f1b0f5239703ef320579ea7cf6e3bc726530ce44fe6caebad2c3d545783616b"},"schema_version":"1.0"},"canonical_sha256":"93be0e4f379040bf10d535bf5c368bb49fe953035267b1b1fa6df0696845544f","source":{"kind":"arxiv","id":"2405.00930","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00930","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00930v2","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00930","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"SO7A4TZXSBAL","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"SO7A4TZXSBAL6EGV","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"SO7A4TZX","created_at":"2026-07-05T09:39:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SO7A4TZXSBAL6EGVGW7VYNULWS","target":"record","payload":{"canonical_record":{"source":{"id":"2405.00930","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-02T01:11:15Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0498907ede3777956458b07b8937bfa5f476117b12a0919e2632bd7095026cdb","abstract_canon_sha256":"0f1b0f5239703ef320579ea7cf6e3bc726530ce44fe6caebad2c3d545783616b"},"schema_version":"1.0"},"canonical_sha256":"93be0e4f379040bf10d535bf5c368bb49fe953035267b1b1fa6df0696845544f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:22.889137Z","signature_b64":"gp3wdEs7zgWNP3ql0bwOjsijlwbN1EyrzQEBqqXnJiW4hce6eZTY1Z435xXJce1CXxFUmkmFjeqMj4xBbqGZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93be0e4f379040bf10d535bf5c368bb49fe953035267b1b1fa6df0696845544f","last_reissued_at":"2026-07-05T09:39:22.888276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:22.888276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.00930","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MBEFdWzDkEz2CWpkbrXStT0S5COIRywoNtllGK4Yrk7xn9aqefpHXGNZeJSjCxFbRV70nRcFXba9pbiIw0sZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:29.895629Z"},"content_sha256":"e05228e748db64015f1bdb6692f65315901bdcae73e14fbd002c919a2682a099","schema_version":"1.0","event_id":"sha256:e05228e748db64015f1bdb6692f65315901bdcae73e14fbd002c919a2682a099"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SO7A4TZXSBAL6EGVGW7VYNULWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAIN-VC: Lightweight Speech Representation Disentanglement for One-shot Voice Conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jianzong Wang, Jing Xiao, Ning Cheng, Pengcheng Li, Xulong Zhang, Yong Zhang","submitted_at":"2024-05-02T01:11:15Z","abstract_excerpt":"One-shot voice conversion aims to change the timbre of any source speech to match that of the unseen target speaker with only one speech sample. Existing methods face difficulties in satisfactory speech representation disentanglement and suffer from sizable networks as some of them leverage numerous complex modules for disentanglement. In this paper, we propose a model named MAIN-VC to effectively disentangle via a concise neural network. The proposed model utilizes Siamese encoders to learn clean representations, further enhanced by the designed mutual information estimator. The Siamese struc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00930","kind":"arxiv","version":2},"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/2405.00930/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":"2026-07-05T09:39:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UOSs68N1VUJvAEyQPSHWMIx2YuCVwMzd/V4+fs+DVne3ipZ+sfcUeRuBbQlpxqg+dGnuyPhtlXPAPuGyNFFcAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:59:29.896142Z"},"content_sha256":"2567a69039f6edf2cc39b6849e45e15e3c78abdb5c477c5c7511e28860742d8a","schema_version":"1.0","event_id":"sha256:2567a69039f6edf2cc39b6849e45e15e3c78abdb5c477c5c7511e28860742d8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SO7A4TZXSBAL6EGVGW7VYNULWS/bundle.json","state_url":"https://pith.science/pith/SO7A4TZXSBAL6EGVGW7VYNULWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SO7A4TZXSBAL6EGVGW7VYNULWS/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":"2026-08-08T12:59:29Z","links":{"resolver":"https://pith.science/pith/SO7A4TZXSBAL6EGVGW7VYNULWS","bundle":"https://pith.science/pith/SO7A4TZXSBAL6EGVGW7VYNULWS/bundle.json","state":"https://pith.science/pith/SO7A4TZXSBAL6EGVGW7VYNULWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SO7A4TZXSBAL6EGVGW7VYNULWS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SO7A4TZXSBAL6EGVGW7VYNULWS","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":"0f1b0f5239703ef320579ea7cf6e3bc726530ce44fe6caebad2c3d545783616b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-02T01:11:15Z","title_canon_sha256":"0498907ede3777956458b07b8937bfa5f476117b12a0919e2632bd7095026cdb"},"schema_version":"1.0","source":{"id":"2405.00930","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00930","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00930v2","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00930","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"pith_short_12","alias_value":"SO7A4TZXSBAL","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"pith_short_16","alias_value":"SO7A4TZXSBAL6EGV","created_at":"2026-07-05T09:39:22Z"},{"alias_kind":"pith_short_8","alias_value":"SO7A4TZX","created_at":"2026-07-05T09:39:22Z"}],"graph_snapshots":[{"event_id":"sha256:2567a69039f6edf2cc39b6849e45e15e3c78abdb5c477c5c7511e28860742d8a","target":"graph","created_at":"2026-07-05T09:39:22Z","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/2405.00930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One-shot voice conversion aims to change the timbre of any source speech to match that of the unseen target speaker with only one speech sample. Existing methods face difficulties in satisfactory speech representation disentanglement and suffer from sizable networks as some of them leverage numerous complex modules for disentanglement. In this paper, we propose a model named MAIN-VC to effectively disentangle via a concise neural network. The proposed model utilizes Siamese encoders to learn clean representations, further enhanced by the designed mutual information estimator. The Siamese struc","authors_text":"Jianzong Wang, Jing Xiao, Ning Cheng, Pengcheng Li, Xulong Zhang, Yong Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-02T01:11:15Z","title":"MAIN-VC: Lightweight Speech Representation Disentanglement for One-shot Voice Conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00930","kind":"arxiv","version":2},"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:e05228e748db64015f1bdb6692f65315901bdcae73e14fbd002c919a2682a099","target":"record","created_at":"2026-07-05T09:39:22Z","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":"0f1b0f5239703ef320579ea7cf6e3bc726530ce44fe6caebad2c3d545783616b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-05-02T01:11:15Z","title_canon_sha256":"0498907ede3777956458b07b8937bfa5f476117b12a0919e2632bd7095026cdb"},"schema_version":"1.0","source":{"id":"2405.00930","kind":"arxiv","version":2}},"canonical_sha256":"93be0e4f379040bf10d535bf5c368bb49fe953035267b1b1fa6df0696845544f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93be0e4f379040bf10d535bf5c368bb49fe953035267b1b1fa6df0696845544f","first_computed_at":"2026-07-05T09:39:22.888276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:39:22.888276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gp3wdEs7zgWNP3ql0bwOjsijlwbN1EyrzQEBqqXnJiW4hce6eZTY1Z435xXJce1CXxFUmkmFjeqMj4xBbqGZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:39:22.889137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00930","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e05228e748db64015f1bdb6692f65315901bdcae73e14fbd002c919a2682a099","sha256:2567a69039f6edf2cc39b6849e45e15e3c78abdb5c477c5c7511e28860742d8a"],"state_sha256":"e31e7c23463cfda6e40e01167b0577637f26f0b8c60b8d259617fbf0bd12fb79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d9bJXSK7Z65lhiZ2rr/To5BrKDCMoWkgJfCS8LEaeQ06VIAPvZPiWaAAYwvioxoaAOgcksH/Pz2xwDJnElgKAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:59:29.900154Z","bundle_sha256":"fe953cd456379decd49862c4f8091aeb2382b1c09875bc611ed8a3561cb3c344"}}