{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YLYFYEOXUZVGDB55FTXJZWQ26L","short_pith_number":"pith:YLYFYEOX","canonical_record":{"source":{"id":"2104.01409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-03T13:53:19Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ff6c8fe1d15c014e558495d329ca807eb497e1ea13e9cd10c874495fdba5512d","abstract_canon_sha256":"c404f61dd236fed8ed660bc6cd3a002310dbe63e1f871ddd56462328b18a0b8f"},"schema_version":"1.0"},"canonical_sha256":"c2f05c11d7a66a6187bd2cee9cda1af2ec824cf6ee2b38018a874f0a76110eb6","source":{"kind":"arxiv","id":"2104.01409","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01409","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01409v1","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01409","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"YLYFYEOXUZVG","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"YLYFYEOXUZVGDB55","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"YLYFYEOX","created_at":"2026-07-05T02:28:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YLYFYEOXUZVGDB55FTXJZWQ26L","target":"record","payload":{"canonical_record":{"source":{"id":"2104.01409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-03T13:53:19Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"ff6c8fe1d15c014e558495d329ca807eb497e1ea13e9cd10c874495fdba5512d","abstract_canon_sha256":"c404f61dd236fed8ed660bc6cd3a002310dbe63e1f871ddd56462328b18a0b8f"},"schema_version":"1.0"},"canonical_sha256":"c2f05c11d7a66a6187bd2cee9cda1af2ec824cf6ee2b38018a874f0a76110eb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:59.730343Z","signature_b64":"9A2avsNqkd5eSc+8vTyvxC9T25rtHGDXKJgFi5Mwo0OJBpBiPdLt4R5hzSk2DjJWiLCb9Xc3s3pCPp7F2JRgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2f05c11d7a66a6187bd2cee9cda1af2ec824cf6ee2b38018a874f0a76110eb6","last_reissued_at":"2026-07-05T02:28:59.729994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:59.729994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.01409","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":"2026-07-05T02:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MgShoiBljjdlRFcLf+gesA6qc9iwNI9BYAJ9NsUjv0QMB1GBDRfwf7CKzR5kOCDA6MPOonWpjRDUmYYBcUmdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:36:40.493678Z"},"content_sha256":"cb5372d38d76ad8173eda45964a94fefd380a09f420aba5fcc35af440c8644fb","schema_version":"1.0","event_id":"sha256:cb5372d38d76ad8173eda45964a94fefd380a09f420aba5fcc35af440c8644fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YLYFYEOXUZVGDB55FTXJZWQ26L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diff-TTS: A Denoising Diffusion Model for Text-to-Speech","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Hyeongju Kim, Myeonghun Jeong, Nam Soo Kim, Sung Jun Cheon","submitted_at":"2021-04-03T13:53:19Z","abstract_excerpt":"Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded in generating human-like speech, there is still room for improvements to its naturalness and architectural efficiency. In this work, we propose a novel non-autoregressive TTS model, namely Diff-TTS, which achieves highly natural and efficient speech synthesis. Given the text, Diff-TTS exploits a denoising diffusion framework to transform the noise signal into a mel-spectrogram via diffusion time steps. In order to learn the mel-spectrogram distribution conditioned on the text, we present a likelihood-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01409","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/2104.01409/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":"2026-07-05T02:28:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hqtWZo3PmtJNzaxWgyCEA3HcUlHIHHUgKMKPXJ2jp+w94ELeEbzvL2cYuNMTjPj22Jpw+MleyvcyylJzQymdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:36:40.494271Z"},"content_sha256":"f732351bf275cd12b1024236cc861388bf8097581f3e5d5740db7f44b8e029fc","schema_version":"1.0","event_id":"sha256:f732351bf275cd12b1024236cc861388bf8097581f3e5d5740db7f44b8e029fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLYFYEOXUZVGDB55FTXJZWQ26L/bundle.json","state_url":"https://pith.science/pith/YLYFYEOXUZVGDB55FTXJZWQ26L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLYFYEOXUZVGDB55FTXJZWQ26L/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":"2026-08-19T08:36:40Z","links":{"resolver":"https://pith.science/pith/YLYFYEOXUZVGDB55FTXJZWQ26L","bundle":"https://pith.science/pith/YLYFYEOXUZVGDB55FTXJZWQ26L/bundle.json","state":"https://pith.science/pith/YLYFYEOXUZVGDB55FTXJZWQ26L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLYFYEOXUZVGDB55FTXJZWQ26L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YLYFYEOXUZVGDB55FTXJZWQ26L","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":"c404f61dd236fed8ed660bc6cd3a002310dbe63e1f871ddd56462328b18a0b8f","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-03T13:53:19Z","title_canon_sha256":"ff6c8fe1d15c014e558495d329ca807eb497e1ea13e9cd10c874495fdba5512d"},"schema_version":"1.0","source":{"id":"2104.01409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01409","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01409v1","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01409","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"YLYFYEOXUZVG","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"YLYFYEOXUZVGDB55","created_at":"2026-07-05T02:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"YLYFYEOX","created_at":"2026-07-05T02:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:f732351bf275cd12b1024236cc861388bf8097581f3e5d5740db7f44b8e029fc","target":"graph","created_at":"2026-07-05T02:28:59Z","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/2104.01409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although neural text-to-speech (TTS) models have attracted a lot of attention and succeeded in generating human-like speech, there is still room for improvements to its naturalness and architectural efficiency. In this work, we propose a novel non-autoregressive TTS model, namely Diff-TTS, which achieves highly natural and efficient speech synthesis. Given the text, Diff-TTS exploits a denoising diffusion framework to transform the noise signal into a mel-spectrogram via diffusion time steps. In order to learn the mel-spectrogram distribution conditioned on the text, we present a likelihood-ba","authors_text":"Byoung Jin Choi, Hyeongju Kim, Myeonghun Jeong, Nam Soo Kim, Sung Jun Cheon","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-03T13:53:19Z","title":"Diff-TTS: A Denoising Diffusion Model for Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01409","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:cb5372d38d76ad8173eda45964a94fefd380a09f420aba5fcc35af440c8644fb","target":"record","created_at":"2026-07-05T02:28:59Z","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":"c404f61dd236fed8ed660bc6cd3a002310dbe63e1f871ddd56462328b18a0b8f","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-03T13:53:19Z","title_canon_sha256":"ff6c8fe1d15c014e558495d329ca807eb497e1ea13e9cd10c874495fdba5512d"},"schema_version":"1.0","source":{"id":"2104.01409","kind":"arxiv","version":1}},"canonical_sha256":"c2f05c11d7a66a6187bd2cee9cda1af2ec824cf6ee2b38018a874f0a76110eb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2f05c11d7a66a6187bd2cee9cda1af2ec824cf6ee2b38018a874f0a76110eb6","first_computed_at":"2026-07-05T02:28:59.729994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:59.729994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9A2avsNqkd5eSc+8vTyvxC9T25rtHGDXKJgFi5Mwo0OJBpBiPdLt4R5hzSk2DjJWiLCb9Xc3s3pCPp7F2JRgCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:59.730343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.01409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb5372d38d76ad8173eda45964a94fefd380a09f420aba5fcc35af440c8644fb","sha256:f732351bf275cd12b1024236cc861388bf8097581f3e5d5740db7f44b8e029fc"],"state_sha256":"935554196b2c546a4e65e3188e01fc31eb3a54e1fa7a5f560c7c498688542aaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ps1Xa9z3+YLOmerf3cn+UNGV5eZLJlZr2QgAbhhDKIeIJi8lmULSPCaLS34UcsoKY7tYRY/fIadEICsGkJVPAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:36:40.499250Z","bundle_sha256":"6bc520357ff5b996327d5456d4a80a2955a9f5fce56497d64d85d0e3484443ff"}}