{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VE4D5GSKN5JF6MWK2FUMT3CK6J","short_pith_number":"pith:VE4D5GSK","canonical_record":{"source":{"id":"2201.00269","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-01-02T01:22:38Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b5cad5ee9d7709dab9aa1f367865c56a101f7210dda1d96715e474007059f140","abstract_canon_sha256":"4d42dca4af3fff255e61d03b6581628343988545c78dce264f05876cd610b331"},"schema_version":"1.0"},"canonical_sha256":"a9383e9a4a6f525f32cad168c9ec4af27614058eb48198aee9aa68cd5f454ac2","source":{"kind":"arxiv","id":"2201.00269","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00269","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00269v1","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00269","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"pith_short_12","alias_value":"VE4D5GSKN5JF","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"pith_short_16","alias_value":"VE4D5GSKN5JF6MWK","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"pith_short_8","alias_value":"VE4D5GSK","created_at":"2026-07-05T03:45:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VE4D5GSKN5JF6MWK2FUMT3CK6J","target":"record","payload":{"canonical_record":{"source":{"id":"2201.00269","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-01-02T01:22:38Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b5cad5ee9d7709dab9aa1f367865c56a101f7210dda1d96715e474007059f140","abstract_canon_sha256":"4d42dca4af3fff255e61d03b6581628343988545c78dce264f05876cd610b331"},"schema_version":"1.0"},"canonical_sha256":"a9383e9a4a6f525f32cad168c9ec4af27614058eb48198aee9aa68cd5f454ac2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:45:00.926800Z","signature_b64":"67/QlV2WCo5+RJZwxOzjfgwvBLLfyzcDyuEW9xWMlVQDrK59+ixYttmt4C66KXDunAv1v5N3uUsm5knBIldzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9383e9a4a6f525f32cad168c9ec4af27614058eb48198aee9aa68cd5f454ac2","last_reissued_at":"2026-07-05T03:45:00.926326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:45:00.926326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.00269","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":"2026-07-05T03:45:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bBzHyrsY+YoXgmzzGf5vV/zs3l9hqff61Hi5TJ3id09nH5q4McE7eVMek8HT0h6YU+51KbhfNmdqk8HgN/IjBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:29:13.655559Z"},"content_sha256":"81387918cbca37b39bfc4c7a736e0a706e06ee5cf16344afe2a17af05303e383","schema_version":"1.0","event_id":"sha256:81387918cbca37b39bfc4c7a736e0a706e06ee5cf16344afe2a17af05303e383"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VE4D5GSKN5JF6MWK2FUMT3CK6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bolong Wen, Hai Li, Haitao Chen, Hongqiang Du, Kaixuan Guo, Lei Xie, Wendong Gan, Ying Yan, Zhichao Wang","submitted_at":"2022-01-02T01:22:38Z","abstract_excerpt":"Prosody modeling is important, but still challenging in expressive voice conversion. As prosody is difficult to model, and other factors, e.g., speaker, environment and content, which are entangled with prosody in speech, should be removed in prosody modeling. In this paper, we present IQDubbing to solve this problem for expressive voice conversion. To model prosody, we leverage the recent advances in discrete self-supervised speech representation (DSSR). Specifically, prosody vector is first extracted from pre-trained VQ-Wav2Vec model, where rich prosody information is embedded while most spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00269","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/2201.00269/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":"2026-07-05T03:45:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vEfLzqZdfwRQPB79UjV+GzX4D0xUrnvyb/j+qV+g7RIJLCO3w1G/AZYT3Z+k8KSgKhLO+phHhVZ5/Uaob7pAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:29:13.656055Z"},"content_sha256":"2709bd5b8324ab4c9dd39224876f1ff74f763bfbcd0ed204715bef2455e399da","schema_version":"1.0","event_id":"sha256:2709bd5b8324ab4c9dd39224876f1ff74f763bfbcd0ed204715bef2455e399da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VE4D5GSKN5JF6MWK2FUMT3CK6J/bundle.json","state_url":"https://pith.science/pith/VE4D5GSKN5JF6MWK2FUMT3CK6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VE4D5GSKN5JF6MWK2FUMT3CK6J/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":"2026-08-05T14:29:13Z","links":{"resolver":"https://pith.science/pith/VE4D5GSKN5JF6MWK2FUMT3CK6J","bundle":"https://pith.science/pith/VE4D5GSKN5JF6MWK2FUMT3CK6J/bundle.json","state":"https://pith.science/pith/VE4D5GSKN5JF6MWK2FUMT3CK6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VE4D5GSKN5JF6MWK2FUMT3CK6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VE4D5GSKN5JF6MWK2FUMT3CK6J","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":"4d42dca4af3fff255e61d03b6581628343988545c78dce264f05876cd610b331","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-01-02T01:22:38Z","title_canon_sha256":"b5cad5ee9d7709dab9aa1f367865c56a101f7210dda1d96715e474007059f140"},"schema_version":"1.0","source":{"id":"2201.00269","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.00269","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"arxiv_version","alias_value":"2201.00269v1","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.00269","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"pith_short_12","alias_value":"VE4D5GSKN5JF","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"pith_short_16","alias_value":"VE4D5GSKN5JF6MWK","created_at":"2026-07-05T03:45:00Z"},{"alias_kind":"pith_short_8","alias_value":"VE4D5GSK","created_at":"2026-07-05T03:45:00Z"}],"graph_snapshots":[{"event_id":"sha256:2709bd5b8324ab4c9dd39224876f1ff74f763bfbcd0ed204715bef2455e399da","target":"graph","created_at":"2026-07-05T03:45:00Z","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/2201.00269/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prosody modeling is important, but still challenging in expressive voice conversion. As prosody is difficult to model, and other factors, e.g., speaker, environment and content, which are entangled with prosody in speech, should be removed in prosody modeling. In this paper, we present IQDubbing to solve this problem for expressive voice conversion. To model prosody, we leverage the recent advances in discrete self-supervised speech representation (DSSR). Specifically, prosody vector is first extracted from pre-trained VQ-Wav2Vec model, where rich prosody information is embedded while most spe","authors_text":"Bolong Wen, Hai Li, Haitao Chen, Hongqiang Du, Kaixuan Guo, Lei Xie, Wendong Gan, Ying Yan, Zhichao Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-01-02T01:22:38Z","title":"IQDUBBING: Prosody modeling based on discrete self-supervised speech representation for expressive voice conversion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.00269","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":"sha256:81387918cbca37b39bfc4c7a736e0a706e06ee5cf16344afe2a17af05303e383","target":"record","created_at":"2026-07-05T03:45:00Z","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":"4d42dca4af3fff255e61d03b6581628343988545c78dce264f05876cd610b331","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-01-02T01:22:38Z","title_canon_sha256":"b5cad5ee9d7709dab9aa1f367865c56a101f7210dda1d96715e474007059f140"},"schema_version":"1.0","source":{"id":"2201.00269","kind":"arxiv","version":1}},"canonical_sha256":"a9383e9a4a6f525f32cad168c9ec4af27614058eb48198aee9aa68cd5f454ac2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9383e9a4a6f525f32cad168c9ec4af27614058eb48198aee9aa68cd5f454ac2","first_computed_at":"2026-07-05T03:45:00.926326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:45:00.926326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67/QlV2WCo5+RJZwxOzjfgwvBLLfyzcDyuEW9xWMlVQDrK59+ixYttmt4C66KXDunAv1v5N3uUsm5knBIldzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:45:00.926800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.00269","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81387918cbca37b39bfc4c7a736e0a706e06ee5cf16344afe2a17af05303e383","sha256:2709bd5b8324ab4c9dd39224876f1ff74f763bfbcd0ed204715bef2455e399da"],"state_sha256":"3f8530c8f31860a6ab4a6e106abefe8a2bd2e311a17b71062ffd5f4e53316c60"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1tFvTD30X3XGjBYjOnc4K0g28QKuHRtgMOJbfz39YZKLSxAZ8r3NwhxquPWsHf1mu+k1Td9wi1BOJSzWp8zGDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:29:13.659011Z","bundle_sha256":"4bc042e221f1bcdbd08baf6b8130b7afad2114a104d6a37aa42a16b38e293f02"}}