{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TJTQMEMYVANHY6EPVUUXPWGODT","short_pith_number":"pith:TJTQMEMY","canonical_record":{"source":{"id":"2307.10550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-20T03:28:06Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"a87e7f7724b36c04b4b24be8c97ee13a05e6e35551cf9cc8e291d30523fe8e5c","abstract_canon_sha256":"51439fe13afe5066cd55baa03f37e9074413b03da2a0e86fc1bd77e5889b38c2"},"schema_version":"1.0"},"canonical_sha256":"9a67061198a81a7c788fad2977d8ce1cf0f43203dc54989f95292bfca263d62c","source":{"kind":"arxiv","id":"2307.10550","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.10550","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2307.10550v1","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10550","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"TJTQMEMYVANH","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"TJTQMEMYVANHY6EP","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"TJTQMEMY","created_at":"2026-07-05T06:33:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TJTQMEMYVANHY6EPVUUXPWGODT","target":"record","payload":{"canonical_record":{"source":{"id":"2307.10550","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-20T03:28:06Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"a87e7f7724b36c04b4b24be8c97ee13a05e6e35551cf9cc8e291d30523fe8e5c","abstract_canon_sha256":"51439fe13afe5066cd55baa03f37e9074413b03da2a0e86fc1bd77e5889b38c2"},"schema_version":"1.0"},"canonical_sha256":"9a67061198a81a7c788fad2977d8ce1cf0f43203dc54989f95292bfca263d62c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:06.863411Z","signature_b64":"gEqptU1XTf9wVVXxri07DUzNXmNkaxffrbwGsBgFTbwKm58BA6/NjEHrAJV3Ncy2bJXBiDDWMRzPwXItvOD9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a67061198a81a7c788fad2977d8ce1cf0f43203dc54989f95292bfca263d62c","last_reissued_at":"2026-07-05T06:33:06.863029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:06.863029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.10550","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":"2026-07-05T06:33:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gJUVlMu4oGiuM1yFjxfMUIwm49VJ65efH/AoAZSsDeA1Y/9TM0opMVv4HPaG8eA68JoQZZSi9s+RWTOb8A6QAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:14:51.644458Z"},"content_sha256":"290ccced77ba83a0b150ff229f089f5c7a9f8b8646bd9f1f54caab8ba14c40b2","schema_version":"1.0","event_id":"sha256:290ccced77ba83a0b150ff229f089f5c7a9f8b8646bd9f1f54caab8ba14c40b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TJTQMEMYVANHY6EPVUUXPWGODT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Daegyeom Kim, Seongho Hong, Yong-Hoon Choi","submitted_at":"2023-07-20T03:28:06Z","abstract_excerpt":"Expressive speech synthesis models are trained by adding corpora with diverse speakers, various emotions, and different speaking styles to the dataset, in order to control various characteristics of speech and generate the desired voice. In this paper, we propose a style control (SC) VALL-E model based on the neural codec language model (called VALL-E), which follows the structure of the generative pretrained transformer 3 (GPT-3). The proposed SC VALL-E takes input from text sentences and prompt audio and is designed to generate controllable speech by not simply mimicking the characteristics "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10550","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/2307.10550/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":"2026-07-05T06:33:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M8KCp2KzrayXfe2omfv8MUiId5502dgMs4wPYV757tKnaa4uoy+MlY1BU/Ep6vOH8DJz945Rh1PEFzsmqpypAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:14:51.644958Z"},"content_sha256":"ebbc14a9f1bb4f018181e30cc6892e20a0446c1d1539d03bd09486d3dee7e87d","schema_version":"1.0","event_id":"sha256:ebbc14a9f1bb4f018181e30cc6892e20a0446c1d1539d03bd09486d3dee7e87d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJTQMEMYVANHY6EPVUUXPWGODT/bundle.json","state_url":"https://pith.science/pith/TJTQMEMYVANHY6EPVUUXPWGODT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJTQMEMYVANHY6EPVUUXPWGODT/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":"2026-08-09T04:14:51Z","links":{"resolver":"https://pith.science/pith/TJTQMEMYVANHY6EPVUUXPWGODT","bundle":"https://pith.science/pith/TJTQMEMYVANHY6EPVUUXPWGODT/bundle.json","state":"https://pith.science/pith/TJTQMEMYVANHY6EPVUUXPWGODT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJTQMEMYVANHY6EPVUUXPWGODT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TJTQMEMYVANHY6EPVUUXPWGODT","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":"51439fe13afe5066cd55baa03f37e9074413b03da2a0e86fc1bd77e5889b38c2","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-20T03:28:06Z","title_canon_sha256":"a87e7f7724b36c04b4b24be8c97ee13a05e6e35551cf9cc8e291d30523fe8e5c"},"schema_version":"1.0","source":{"id":"2307.10550","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.10550","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2307.10550v1","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10550","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"TJTQMEMYVANH","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"TJTQMEMYVANHY6EP","created_at":"2026-07-05T06:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"TJTQMEMY","created_at":"2026-07-05T06:33:06Z"}],"graph_snapshots":[{"event_id":"sha256:ebbc14a9f1bb4f018181e30cc6892e20a0446c1d1539d03bd09486d3dee7e87d","target":"graph","created_at":"2026-07-05T06:33:06Z","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/2307.10550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive speech synthesis models are trained by adding corpora with diverse speakers, various emotions, and different speaking styles to the dataset, in order to control various characteristics of speech and generate the desired voice. In this paper, we propose a style control (SC) VALL-E model based on the neural codec language model (called VALL-E), which follows the structure of the generative pretrained transformer 3 (GPT-3). The proposed SC VALL-E takes input from text sentences and prompt audio and is designed to generate controllable speech by not simply mimicking the characteristics ","authors_text":"Daegyeom Kim, Seongho Hong, Yong-Hoon Choi","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-20T03:28:06Z","title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10550","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":"sha256:290ccced77ba83a0b150ff229f089f5c7a9f8b8646bd9f1f54caab8ba14c40b2","target":"record","created_at":"2026-07-05T06:33:06Z","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":"51439fe13afe5066cd55baa03f37e9074413b03da2a0e86fc1bd77e5889b38c2","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-07-20T03:28:06Z","title_canon_sha256":"a87e7f7724b36c04b4b24be8c97ee13a05e6e35551cf9cc8e291d30523fe8e5c"},"schema_version":"1.0","source":{"id":"2307.10550","kind":"arxiv","version":1}},"canonical_sha256":"9a67061198a81a7c788fad2977d8ce1cf0f43203dc54989f95292bfca263d62c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a67061198a81a7c788fad2977d8ce1cf0f43203dc54989f95292bfca263d62c","first_computed_at":"2026-07-05T06:33:06.863029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:06.863029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gEqptU1XTf9wVVXxri07DUzNXmNkaxffrbwGsBgFTbwKm58BA6/NjEHrAJV3Ncy2bJXBiDDWMRzPwXItvOD9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:06.863411Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.10550","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:290ccced77ba83a0b150ff229f089f5c7a9f8b8646bd9f1f54caab8ba14c40b2","sha256:ebbc14a9f1bb4f018181e30cc6892e20a0446c1d1539d03bd09486d3dee7e87d"],"state_sha256":"f6fd8f79db7cb57cf92dc647d6d78c3ffa8cfd9119fd2b959c3afb16690489e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6tu87+V5QPIyjT1P0QSDxCQ2OSchsDed0tsi1NeiMURcCmb3QRbvE75aLOX7wbPkhnhhvbEpHc7ECIdGcY02Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:14:51.648686Z","bundle_sha256":"5219eaa2080ed040f68bcd0b46f57754992cdccd5e19ad956a4eef478c293f71"}}