{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CFO7OMDASDY75G2MDXHUAUPKS7","short_pith_number":"pith:CFO7OMDA","canonical_record":{"source":{"id":"2303.02939","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-06T07:17:15Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0e58abc0e81f68cc83b11542cf2321a0ad1c3b95d20eaa73df604a7c6b02de09","abstract_canon_sha256":"539efabe5f71fb6bd7894bc4bf2a1a992a7d1704e0c4e8e1b478d0f429bbe639"},"schema_version":"1.0"},"canonical_sha256":"115df7306090f1fe9b4c1dcf4051ea97e0c573c6f8f0a3b6180b5c51323e59f0","source":{"kind":"arxiv","id":"2303.02939","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02939","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02939v3","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02939","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"CFO7OMDASDY7","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"pith_short_16","alias_value":"CFO7OMDASDY75G2M","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"pith_short_8","alias_value":"CFO7OMDA","created_at":"2026-07-05T05:49:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CFO7OMDASDY75G2MDXHUAUPKS7","target":"record","payload":{"canonical_record":{"source":{"id":"2303.02939","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-06T07:17:15Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"0e58abc0e81f68cc83b11542cf2321a0ad1c3b95d20eaa73df604a7c6b02de09","abstract_canon_sha256":"539efabe5f71fb6bd7894bc4bf2a1a992a7d1704e0c4e8e1b478d0f429bbe639"},"schema_version":"1.0"},"canonical_sha256":"115df7306090f1fe9b4c1dcf4051ea97e0c573c6f8f0a3b6180b5c51323e59f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:18.681153Z","signature_b64":"eUh3CPb8UiOWnWa+YNCr2LH/82lqUCxEkSddwK95laSEFEH24yIIiG/HW6dwXYh86FzUkqTiI1PGNohuqHnZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"115df7306090f1fe9b4c1dcf4051ea97e0c573c6f8f0a3b6180b5c51323e59f0","last_reissued_at":"2026-07-05T05:49:18.680637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:18.680637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.02939","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:49:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ox0cfKXftqqDRa+Y7gjhjBf9HczNiq748UakHLusFvSRNRscQvH+d5KylzvpZ9H8XWoAE9uGlRv7lbYA9eO2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:16:16.930521Z"},"content_sha256":"f3038e176ca015627a3c55561cd9282872395f74b8466ffdb04afb74661d8e7a","schema_version":"1.0","event_id":"sha256:f3038e176ca015627a3c55561cd9282872395f74b8466ffdb04afb74661d8e7a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CFO7OMDASDY75G2MDXHUAUPKS7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Edward Lin, Lei He, Linquan Liu, Ruiqing Xue, Sheng Zhao, Xu Tan, Yanqing Liu","submitted_at":"2023-03-06T07:17:15Z","abstract_excerpt":"Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate representations to bridge acoustic model and vocoder, which suffers from two limitations: 1) the continuous acoustic frames are hard to predict with phoneme only, and acoustic information like duration or pitch is also needed to solve the one-to-many problem, which is not easy to scale on large scale and noise datasets; 2) to achieve diverse speech output base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02939","kind":"arxiv","version":3},"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/2303.02939/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":"2026-07-05T05:49:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wL2n45ejx4NOYX++7Dh2PoOmqirvUdhZ4BskpFB9VaB3564MnqaifJssK2d1pe7FXefl2Q0ftnl75RaErw1jAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:16:16.931352Z"},"content_sha256":"674fa7aa995fbcdc91c4f9c610bcd210d05b1b8311b9e10c2f86eb3eaf081ea9","schema_version":"1.0","event_id":"sha256:674fa7aa995fbcdc91c4f9c610bcd210d05b1b8311b9e10c2f86eb3eaf081ea9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CFO7OMDASDY75G2MDXHUAUPKS7/bundle.json","state_url":"https://pith.science/pith/CFO7OMDASDY75G2MDXHUAUPKS7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CFO7OMDASDY75G2MDXHUAUPKS7/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":"2026-08-10T18:16:16Z","links":{"resolver":"https://pith.science/pith/CFO7OMDASDY75G2MDXHUAUPKS7","bundle":"https://pith.science/pith/CFO7OMDASDY75G2MDXHUAUPKS7/bundle.json","state":"https://pith.science/pith/CFO7OMDASDY75G2MDXHUAUPKS7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CFO7OMDASDY75G2MDXHUAUPKS7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CFO7OMDASDY75G2MDXHUAUPKS7","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":"539efabe5f71fb6bd7894bc4bf2a1a992a7d1704e0c4e8e1b478d0f429bbe639","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-06T07:17:15Z","title_canon_sha256":"0e58abc0e81f68cc83b11542cf2321a0ad1c3b95d20eaa73df604a7c6b02de09"},"schema_version":"1.0","source":{"id":"2303.02939","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02939","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02939v3","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02939","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"CFO7OMDASDY7","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"pith_short_16","alias_value":"CFO7OMDASDY75G2M","created_at":"2026-07-05T05:49:18Z"},{"alias_kind":"pith_short_8","alias_value":"CFO7OMDA","created_at":"2026-07-05T05:49:18Z"}],"graph_snapshots":[{"event_id":"sha256:674fa7aa995fbcdc91c4f9c610bcd210d05b1b8311b9e10c2f86eb3eaf081ea9","target":"graph","created_at":"2026-07-05T05:49:18Z","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/2303.02939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural text-to-speech (TTS) generally consists of cascaded architecture with separately optimized acoustic model and vocoder, or end-to-end architecture with continuous mel-spectrograms or self-extracted speech frames as the intermediate representations to bridge acoustic model and vocoder, which suffers from two limitations: 1) the continuous acoustic frames are hard to predict with phoneme only, and acoustic information like duration or pitch is also needed to solve the one-to-many problem, which is not easy to scale on large scale and noise datasets; 2) to achieve diverse speech output base","authors_text":"Edward Lin, Lei He, Linquan Liu, Ruiqing Xue, Sheng Zhao, Xu Tan, Yanqing Liu","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-06T07:17:15Z","title":"FoundationTTS: Text-to-Speech for ASR Customization with Generative Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02939","kind":"arxiv","version":3},"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:f3038e176ca015627a3c55561cd9282872395f74b8466ffdb04afb74661d8e7a","target":"record","created_at":"2026-07-05T05:49:18Z","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":"539efabe5f71fb6bd7894bc4bf2a1a992a7d1704e0c4e8e1b478d0f429bbe639","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2023-03-06T07:17:15Z","title_canon_sha256":"0e58abc0e81f68cc83b11542cf2321a0ad1c3b95d20eaa73df604a7c6b02de09"},"schema_version":"1.0","source":{"id":"2303.02939","kind":"arxiv","version":3}},"canonical_sha256":"115df7306090f1fe9b4c1dcf4051ea97e0c573c6f8f0a3b6180b5c51323e59f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"115df7306090f1fe9b4c1dcf4051ea97e0c573c6f8f0a3b6180b5c51323e59f0","first_computed_at":"2026-07-05T05:49:18.680637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:18.680637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eUh3CPb8UiOWnWa+YNCr2LH/82lqUCxEkSddwK95laSEFEH24yIIiG/HW6dwXYh86FzUkqTiI1PGNohuqHnZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:18.681153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.02939","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3038e176ca015627a3c55561cd9282872395f74b8466ffdb04afb74661d8e7a","sha256:674fa7aa995fbcdc91c4f9c610bcd210d05b1b8311b9e10c2f86eb3eaf081ea9"],"state_sha256":"a47df5b29ec41129b4bf9401ae59a6fcb915e9dc6d6311f6f9d4a96e71f5ffa9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qusWrmappbXCdNt3Bem351Z+fm2UO+yaQLUGMRLJiu8Tznvsoezz7ePuvweaOICcllg84O7eXK6AD/t/mzPIBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:16:16.936051Z","bundle_sha256":"dfdbcd35c04cf2d4c906c38bda2ce290a83154adf76206fe829a2c83242b58f2"}}