{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ONDHC3O66V3GBJ4XQTMZZGFADI","short_pith_number":"pith:ONDHC3O6","canonical_record":{"source":{"id":"2103.09474","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-17T07:11:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"76c43e8d49f8b331106368ed7fe3de26f1b10db28e965517ad591539dc732fd0","abstract_canon_sha256":"67b52fbe5c7c1f6fbf8379bd5b01143d4ec709d1c80bebf7624e2a2019fd46ad"},"schema_version":"1.0"},"canonical_sha256":"7346716ddef57660a79784d99c98a01a14a506e226d2ce1436a33f9267bd0fc5","source":{"kind":"arxiv","id":"2103.09474","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.09474","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"2103.09474v4","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09474","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"ONDHC3O66V3G","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"pith_short_16","alias_value":"ONDHC3O66V3GBJ4X","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"pith_short_8","alias_value":"ONDHC3O6","created_at":"2026-07-05T02:52:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ONDHC3O66V3GBJ4XQTMZZGFADI","target":"record","payload":{"canonical_record":{"source":{"id":"2103.09474","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-17T07:11:09Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"76c43e8d49f8b331106368ed7fe3de26f1b10db28e965517ad591539dc732fd0","abstract_canon_sha256":"67b52fbe5c7c1f6fbf8379bd5b01143d4ec709d1c80bebf7624e2a2019fd46ad"},"schema_version":"1.0"},"canonical_sha256":"7346716ddef57660a79784d99c98a01a14a506e226d2ce1436a33f9267bd0fc5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:15.573541Z","signature_b64":"MdT0KpVBbSgdOfuqOf2k81Y+lZKMZsqow+w62zEU6lFyE5PgTMQ8VMFyVP3M4Z5Wa19jrqwdVPjvNo61++n5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7346716ddef57660a79784d99c98a01a14a506e226d2ce1436a33f9267bd0fc5","last_reissued_at":"2026-07-05T02:52:15.573200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:15.573200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.09474","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6102TCa9+r5LaTs6UGMVyw1katG/qU88vStncEQveDeie9IYQUsIOLS8xYRBByZXBDqrVRBDm8FXPEAb/m0QDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T13:52:25.034594Z"},"content_sha256":"c0e79f2f1f5621995ce09d0239df4fc310b6431fc839d1b33b07b6d24316bacb","schema_version":"1.0","event_id":"sha256:c0e79f2f1f5621995ce09d0239df4fc310b6431fc839d1b33b07b6d24316bacb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ONDHC3O66V3GBJ4XQTMZZGFADI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Daeyoung Kim, Keon Lee, Kyumin Park","submitted_at":"2021-03-17T07:11:09Z","abstract_excerpt":"Previous works on neural text-to-speech (TTS) have been addressed on limited speed in training and inference time, robustness for difficult synthesis conditions, expressiveness, and controllability. Although several approaches resolve some limitations, there has been no attempt to solve all weaknesses at once. In this paper, we propose STYLER, an expressive and controllable TTS framework with high-speed and robust synthesis. Our novel audio-text aligning method called Mel Calibrator and excluding autoregressive decoding enable rapid training and inference and robust synthesis on unseen data. A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09474","kind":"arxiv","version":4},"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/2103.09474/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":"2026-07-05T02:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NuvO8zDinWQ3LzLAPMjtfODiQUhFI8RVEuBKoVFHNFq7JDfp9JYgy/F7JytdgPgGV8zU287GzbZmoRXkzsOXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T13:52:25.035116Z"},"content_sha256":"dcaa89332c74e655072d69084474a5e8a952be310ef5ab03e933460704b129f7","schema_version":"1.0","event_id":"sha256:dcaa89332c74e655072d69084474a5e8a952be310ef5ab03e933460704b129f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ONDHC3O66V3GBJ4XQTMZZGFADI/bundle.json","state_url":"https://pith.science/pith/ONDHC3O66V3GBJ4XQTMZZGFADI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ONDHC3O66V3GBJ4XQTMZZGFADI/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":"2026-08-16T13:52:25Z","links":{"resolver":"https://pith.science/pith/ONDHC3O66V3GBJ4XQTMZZGFADI","bundle":"https://pith.science/pith/ONDHC3O66V3GBJ4XQTMZZGFADI/bundle.json","state":"https://pith.science/pith/ONDHC3O66V3GBJ4XQTMZZGFADI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ONDHC3O66V3GBJ4XQTMZZGFADI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ONDHC3O66V3GBJ4XQTMZZGFADI","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":"67b52fbe5c7c1f6fbf8379bd5b01143d4ec709d1c80bebf7624e2a2019fd46ad","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-17T07:11:09Z","title_canon_sha256":"76c43e8d49f8b331106368ed7fe3de26f1b10db28e965517ad591539dc732fd0"},"schema_version":"1.0","source":{"id":"2103.09474","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.09474","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"2103.09474v4","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09474","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"ONDHC3O66V3G","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"pith_short_16","alias_value":"ONDHC3O66V3GBJ4X","created_at":"2026-07-05T02:52:15Z"},{"alias_kind":"pith_short_8","alias_value":"ONDHC3O6","created_at":"2026-07-05T02:52:15Z"}],"graph_snapshots":[{"event_id":"sha256:dcaa89332c74e655072d69084474a5e8a952be310ef5ab03e933460704b129f7","target":"graph","created_at":"2026-07-05T02:52:15Z","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/2103.09474/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Previous works on neural text-to-speech (TTS) have been addressed on limited speed in training and inference time, robustness for difficult synthesis conditions, expressiveness, and controllability. Although several approaches resolve some limitations, there has been no attempt to solve all weaknesses at once. In this paper, we propose STYLER, an expressive and controllable TTS framework with high-speed and robust synthesis. Our novel audio-text aligning method called Mel Calibrator and excluding autoregressive decoding enable rapid training and inference and robust synthesis on unseen data. A","authors_text":"Daeyoung Kim, Keon Lee, Kyumin Park","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-17T07:11:09Z","title":"STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09474","kind":"arxiv","version":4},"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:c0e79f2f1f5621995ce09d0239df4fc310b6431fc839d1b33b07b6d24316bacb","target":"record","created_at":"2026-07-05T02:52:15Z","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":"67b52fbe5c7c1f6fbf8379bd5b01143d4ec709d1c80bebf7624e2a2019fd46ad","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-17T07:11:09Z","title_canon_sha256":"76c43e8d49f8b331106368ed7fe3de26f1b10db28e965517ad591539dc732fd0"},"schema_version":"1.0","source":{"id":"2103.09474","kind":"arxiv","version":4}},"canonical_sha256":"7346716ddef57660a79784d99c98a01a14a506e226d2ce1436a33f9267bd0fc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7346716ddef57660a79784d99c98a01a14a506e226d2ce1436a33f9267bd0fc5","first_computed_at":"2026-07-05T02:52:15.573200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:15.573200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MdT0KpVBbSgdOfuqOf2k81Y+lZKMZsqow+w62zEU6lFyE5PgTMQ8VMFyVP3M4Z5Wa19jrqwdVPjvNo61++n5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:15.573541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.09474","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0e79f2f1f5621995ce09d0239df4fc310b6431fc839d1b33b07b6d24316bacb","sha256:dcaa89332c74e655072d69084474a5e8a952be310ef5ab03e933460704b129f7"],"state_sha256":"2af920ef27b6d804015ae874703a8631c877a47971fdc7f4e1a940ea0c752115"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LDTN4qMcTED60lNDy6ystla+fAmKhcBtCRUaZlYvg+T+vxZX49yg4y9ycsIIcwog+lgX/DS6JNR+Z5A8/hBfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T13:52:25.039881Z","bundle_sha256":"f45729bfa70c4dc4a6fd46b2129c95d1a20979c76a02c87a736a28defe931a83"}}