{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ORVHXAP25GQMM6LQO46RNBRDET","short_pith_number":"pith:ORVHXAP2","canonical_record":{"source":{"id":"2005.03295","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-07T07:37:31Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"5da8d599ef3f110c6e4303a213f7c8c41fe0679c681df0ae6813bfc820df80d9","abstract_canon_sha256":"be577bf2b2acb489a341bfce21262b463cd8fe8842ba30f01fd78c9f080f749d"},"schema_version":"1.0"},"canonical_sha256":"746a7b81fae9a0c67970773d16862324c0f62912ac5798d761cc0093c5edd85d","source":{"kind":"arxiv","id":"2005.03295","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.03295","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"2005.03295v2","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03295","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"ORVHXAP25GQM","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"pith_short_16","alias_value":"ORVHXAP25GQMM6LQ","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"pith_short_8","alias_value":"ORVHXAP2","created_at":"2026-07-05T01:27:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ORVHXAP25GQMM6LQO46RNBRDET","target":"record","payload":{"canonical_record":{"source":{"id":"2005.03295","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-07T07:37:31Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"5da8d599ef3f110c6e4303a213f7c8c41fe0679c681df0ae6813bfc820df80d9","abstract_canon_sha256":"be577bf2b2acb489a341bfce21262b463cd8fe8842ba30f01fd78c9f080f749d"},"schema_version":"1.0"},"canonical_sha256":"746a7b81fae9a0c67970773d16862324c0f62912ac5798d761cc0093c5edd85d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:03.301746Z","signature_b64":"0Nf9sh9bf46gH+NLdSFRP3lxgoog7XHwwGvAOxpUEpKnFjZe0JiaYDyozZ87h0eB33yNtzS775N1TCX/X5usAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"746a7b81fae9a0c67970773d16862324c0f62912ac5798d761cc0093c5edd85d","last_reissued_at":"2026-07-05T01:27:03.301350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:03.301350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.03295","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":"2026-07-05T01:27:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j4lC2/oeJmZkaLbn0utIa1TjCvAGeLBRM3fWVJC+avQRBNOwH9xQh6I5426Yerq0xDwsJ/ms8AQOeg8u/8WvAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:25:49.408789Z"},"content_sha256":"51e09f3900c19b83e8756a4f33ca8e43484881cbfd80eeb6aaa94f09af919e66","schema_version":"1.0","event_id":"sha256:51e09f3900c19b83e8756a4f33ca8e43484881cbfd80eeb6aaa94f09af919e66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ORVHXAP25GQMM6LQO46RNBRDET","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cotatron: Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Doo-young Kim, Myun-chul Joe, Seung-won Park","submitted_at":"2020-05-07T07:37:31Z","abstract_excerpt":"We propose Cotatron, a transcription-guided speech encoder for speaker-independent linguistic representation. Cotatron is based on the multispeaker TTS architecture and can be trained with conventional TTS datasets. We train a voice conversion system to reconstruct speech with Cotatron features, which is similar to the previous methods based on Phonetic Posteriorgram (PPG). By training and evaluating our system with 108 speakers from the VCTK dataset, we outperform the previous method in terms of both naturalness and speaker similarity. Our system can also convert speech from speakers that are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03295","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/2005.03295/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":"2026-07-05T01:27:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V7iVVwbAXK7VZXwG9OdWCPdKaSFxWyirEi9cI816Y0EPHDrTWhPhOG49/oIO3t0ha19CXcx/QOjphkTWSy97AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T15:25:49.409598Z"},"content_sha256":"16d46b392c62ba15bac4eab443a31fed914c1892617b6c9b3b24352334159e64","schema_version":"1.0","event_id":"sha256:16d46b392c62ba15bac4eab443a31fed914c1892617b6c9b3b24352334159e64"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORVHXAP25GQMM6LQO46RNBRDET/bundle.json","state_url":"https://pith.science/pith/ORVHXAP25GQMM6LQO46RNBRDET/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORVHXAP25GQMM6LQO46RNBRDET/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":"2026-08-20T15:25:49Z","links":{"resolver":"https://pith.science/pith/ORVHXAP25GQMM6LQO46RNBRDET","bundle":"https://pith.science/pith/ORVHXAP25GQMM6LQO46RNBRDET/bundle.json","state":"https://pith.science/pith/ORVHXAP25GQMM6LQO46RNBRDET/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORVHXAP25GQMM6LQO46RNBRDET/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ORVHXAP25GQMM6LQO46RNBRDET","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":"be577bf2b2acb489a341bfce21262b463cd8fe8842ba30f01fd78c9f080f749d","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-07T07:37:31Z","title_canon_sha256":"5da8d599ef3f110c6e4303a213f7c8c41fe0679c681df0ae6813bfc820df80d9"},"schema_version":"1.0","source":{"id":"2005.03295","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.03295","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"arxiv_version","alias_value":"2005.03295v2","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.03295","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"pith_short_12","alias_value":"ORVHXAP25GQM","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"pith_short_16","alias_value":"ORVHXAP25GQMM6LQ","created_at":"2026-07-05T01:27:03Z"},{"alias_kind":"pith_short_8","alias_value":"ORVHXAP2","created_at":"2026-07-05T01:27:03Z"}],"graph_snapshots":[{"event_id":"sha256:16d46b392c62ba15bac4eab443a31fed914c1892617b6c9b3b24352334159e64","target":"graph","created_at":"2026-07-05T01:27:03Z","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/2005.03295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Cotatron, a transcription-guided speech encoder for speaker-independent linguistic representation. Cotatron is based on the multispeaker TTS architecture and can be trained with conventional TTS datasets. We train a voice conversion system to reconstruct speech with Cotatron features, which is similar to the previous methods based on Phonetic Posteriorgram (PPG). By training and evaluating our system with 108 speakers from the VCTK dataset, we outperform the previous method in terms of both naturalness and speaker similarity. Our system can also convert speech from speakers that are","authors_text":"Doo-young Kim, Myun-chul Joe, Seung-won Park","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-07T07:37:31Z","title":"Cotatron: Transcription-Guided Speech Encoder for Any-to-Many Voice Conversion without Parallel Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.03295","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":"sha256:51e09f3900c19b83e8756a4f33ca8e43484881cbfd80eeb6aaa94f09af919e66","target":"record","created_at":"2026-07-05T01:27:03Z","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":"be577bf2b2acb489a341bfce21262b463cd8fe8842ba30f01fd78c9f080f749d","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-07T07:37:31Z","title_canon_sha256":"5da8d599ef3f110c6e4303a213f7c8c41fe0679c681df0ae6813bfc820df80d9"},"schema_version":"1.0","source":{"id":"2005.03295","kind":"arxiv","version":2}},"canonical_sha256":"746a7b81fae9a0c67970773d16862324c0f62912ac5798d761cc0093c5edd85d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"746a7b81fae9a0c67970773d16862324c0f62912ac5798d761cc0093c5edd85d","first_computed_at":"2026-07-05T01:27:03.301350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:03.301350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Nf9sh9bf46gH+NLdSFRP3lxgoog7XHwwGvAOxpUEpKnFjZe0JiaYDyozZ87h0eB33yNtzS775N1TCX/X5usAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:03.301746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.03295","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51e09f3900c19b83e8756a4f33ca8e43484881cbfd80eeb6aaa94f09af919e66","sha256:16d46b392c62ba15bac4eab443a31fed914c1892617b6c9b3b24352334159e64"],"state_sha256":"f3e1c056213b9c716b110d2a79c5e4ce7300f13dd6e7ac358c6342b155300ba0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2XxKsK+hiL5pwP0E+LnqWXkiZu4E+t5sXae3S6rtk/zq1I7mYf0/PQtM1bmqQF0OwjW8sy68yqjp2+FPThACCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T15:25:49.418076Z","bundle_sha256":"efd5d4a68739cc55a22203c821ef4d1305d2a1999d7eab6686c141b57071ec07"}}