{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Q6XMLC5WQ2J7KRO3XC732CYZW6","short_pith_number":"pith:Q6XMLC5W","canonical_record":{"source":{"id":"2010.14150","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-27T09:21:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be211b3e32fee1f8a93c84fdc0259fd423835a578a74481708b3428820fa2e81","abstract_canon_sha256":"bcd1e29bbbe83da5c6898a1cba648e1077a270403793de57f80bb8d8109258eb"},"schema_version":"1.0"},"canonical_sha256":"87aec58bb68693f545dbb8bfbd0b19b79fcb5c27d69a191347d7792e1c2dc054","source":{"kind":"arxiv","id":"2010.14150","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14150","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14150v2","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14150","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"pith_short_12","alias_value":"Q6XMLC5WQ2J7","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6XMLC5WQ2J7KRO3","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6XMLC5W","created_at":"2026-07-05T02:36:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Q6XMLC5WQ2J7KRO3XC732CYZW6","target":"record","payload":{"canonical_record":{"source":{"id":"2010.14150","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-27T09:21:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be211b3e32fee1f8a93c84fdc0259fd423835a578a74481708b3428820fa2e81","abstract_canon_sha256":"bcd1e29bbbe83da5c6898a1cba648e1077a270403793de57f80bb8d8109258eb"},"schema_version":"1.0"},"canonical_sha256":"87aec58bb68693f545dbb8bfbd0b19b79fcb5c27d69a191347d7792e1c2dc054","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:46.313117Z","signature_b64":"avLoILDm05/7DRZvEd2fs3+Aoxi+4VS2JLBBhNd7KABanwoRxeLgHtxyJNdASXaL/c3NMNySftynt20Nw7QADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87aec58bb68693f545dbb8bfbd0b19b79fcb5c27d69a191347d7792e1c2dc054","last_reissued_at":"2026-07-05T02:36:46.312613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:46.312613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.14150","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":"2026-07-05T02:36:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vLGHZQez724QW9hyopAx0DUH+Dou3tjUgp4SU8hsHtCH7gOsWKa3cl9YoDXA47KpNim6i/Bwy9mPXvVk9zGBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:24:11.633387Z"},"content_sha256":"1dc989b746425b129a379919c1918fe45ff6c2f3448ab362abe1b10c097e0f20","schema_version":"1.0","event_id":"sha256:1dc989b746425b129a379919c1918fe45ff6c2f3448ab362abe1b10c097e0f20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Q6XMLC5WQ2J7KRO3XC732CYZW6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.AS","authors_text":"Chung-Ming Chien, Hung-yi Lee, Jheng-Hao Lin, Lin-shan Lee, Yist Y. Lin","submitted_at":"2020-10-27T09:21:03Z","abstract_excerpt":"Any-to-any voice conversion aims to convert the voice from and to any speakers even unseen during training, which is much more challenging compared to one-to-one or many-to-many tasks, but much more attractive in real-world scenarios. In this paper we proposed FragmentVC, in which the latent phonetic structure of the utterance from the source speaker is obtained from Wav2Vec 2.0, while the spectral features of the utterance(s) from the target speaker are obtained from log mel-spectrograms. By aligning the hidden structures of the two different feature spaces with a two-stage training process, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14150","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/2010.14150/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":"2026-07-05T02:36:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M7xjgwvvjbDaHuAbDd6xIQr5nhWL2U9j0fHlZpXRubLRjmxQs0Qvgc+w29yylwoWpjckeG96yyd05bGQcGhRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:24:11.633887Z"},"content_sha256":"9147717428edc05a0455ba404f33a1500331405343a505d59f70a295feb30e24","schema_version":"1.0","event_id":"sha256:9147717428edc05a0455ba404f33a1500331405343a505d59f70a295feb30e24"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6XMLC5WQ2J7KRO3XC732CYZW6/bundle.json","state_url":"https://pith.science/pith/Q6XMLC5WQ2J7KRO3XC732CYZW6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6XMLC5WQ2J7KRO3XC732CYZW6/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":"2026-08-23T17:24:11Z","links":{"resolver":"https://pith.science/pith/Q6XMLC5WQ2J7KRO3XC732CYZW6","bundle":"https://pith.science/pith/Q6XMLC5WQ2J7KRO3XC732CYZW6/bundle.json","state":"https://pith.science/pith/Q6XMLC5WQ2J7KRO3XC732CYZW6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6XMLC5WQ2J7KRO3XC732CYZW6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Q6XMLC5WQ2J7KRO3XC732CYZW6","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":"bcd1e29bbbe83da5c6898a1cba648e1077a270403793de57f80bb8d8109258eb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-27T09:21:03Z","title_canon_sha256":"be211b3e32fee1f8a93c84fdc0259fd423835a578a74481708b3428820fa2e81"},"schema_version":"1.0","source":{"id":"2010.14150","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14150","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14150v2","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14150","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"pith_short_12","alias_value":"Q6XMLC5WQ2J7","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"pith_short_16","alias_value":"Q6XMLC5WQ2J7KRO3","created_at":"2026-07-05T02:36:46Z"},{"alias_kind":"pith_short_8","alias_value":"Q6XMLC5W","created_at":"2026-07-05T02:36:46Z"}],"graph_snapshots":[{"event_id":"sha256:9147717428edc05a0455ba404f33a1500331405343a505d59f70a295feb30e24","target":"graph","created_at":"2026-07-05T02:36:46Z","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/2010.14150/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Any-to-any voice conversion aims to convert the voice from and to any speakers even unseen during training, which is much more challenging compared to one-to-one or many-to-many tasks, but much more attractive in real-world scenarios. In this paper we proposed FragmentVC, in which the latent phonetic structure of the utterance from the source speaker is obtained from Wav2Vec 2.0, while the spectral features of the utterance(s) from the target speaker are obtained from log mel-spectrograms. By aligning the hidden structures of the two different feature spaces with a two-stage training process, ","authors_text":"Chung-Ming Chien, Hung-yi Lee, Jheng-Hao Lin, Lin-shan Lee, Yist Y. Lin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-27T09:21:03Z","title":"FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14150","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":"sha256:1dc989b746425b129a379919c1918fe45ff6c2f3448ab362abe1b10c097e0f20","target":"record","created_at":"2026-07-05T02:36:46Z","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":"bcd1e29bbbe83da5c6898a1cba648e1077a270403793de57f80bb8d8109258eb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-10-27T09:21:03Z","title_canon_sha256":"be211b3e32fee1f8a93c84fdc0259fd423835a578a74481708b3428820fa2e81"},"schema_version":"1.0","source":{"id":"2010.14150","kind":"arxiv","version":2}},"canonical_sha256":"87aec58bb68693f545dbb8bfbd0b19b79fcb5c27d69a191347d7792e1c2dc054","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87aec58bb68693f545dbb8bfbd0b19b79fcb5c27d69a191347d7792e1c2dc054","first_computed_at":"2026-07-05T02:36:46.312613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:36:46.312613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"avLoILDm05/7DRZvEd2fs3+Aoxi+4VS2JLBBhNd7KABanwoRxeLgHtxyJNdASXaL/c3NMNySftynt20Nw7QADA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:36:46.313117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.14150","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dc989b746425b129a379919c1918fe45ff6c2f3448ab362abe1b10c097e0f20","sha256:9147717428edc05a0455ba404f33a1500331405343a505d59f70a295feb30e24"],"state_sha256":"57658c8f5f193ca740446e33d4864860f50d9d69fbd80c4aba66a45381e82b1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NTUDSlsQIZXuL/bWk2E9efC9jSTPiI9mGABAQPfDjRTfKDRCD17DLRtY7fRh7NfsS2PVVD2JZZ2HiaF/yRXmBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:24:11.637378Z","bundle_sha256":"75c5e9235f65858ab48bb0a3f9e469cfd2f04ad701a67a3d72faa45064f90039"}}