{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AWVLDGCMCODQCJ2G5KZHVOSXYQ","short_pith_number":"pith:AWVLDGCM","canonical_record":{"source":{"id":"2301.08810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-20T21:36:16Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"869b935155d74b34a5f63a0553eccb3deae6eaf5333b71da9b7e624b59c2d0d2","abstract_canon_sha256":"b4cd5efb4888780a87d987d7fb417f3e9b3859acd8137b795bba957afb3a8973"},"schema_version":"1.0"},"canonical_sha256":"05aab1984c1387012746eab27aba57c4058648a2fe0ec39451b9efc130b2f7b4","source":{"kind":"arxiv","id":"2301.08810","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08810","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08810v1","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08810","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"pith_short_12","alias_value":"AWVLDGCMCODQ","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"pith_short_16","alias_value":"AWVLDGCMCODQCJ2G","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"pith_short_8","alias_value":"AWVLDGCM","created_at":"2026-07-05T05:34:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AWVLDGCMCODQCJ2G5KZHVOSXYQ","target":"record","payload":{"canonical_record":{"source":{"id":"2301.08810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-20T21:36:16Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"869b935155d74b34a5f63a0553eccb3deae6eaf5333b71da9b7e624b59c2d0d2","abstract_canon_sha256":"b4cd5efb4888780a87d987d7fb417f3e9b3859acd8137b795bba957afb3a8973"},"schema_version":"1.0"},"canonical_sha256":"05aab1984c1387012746eab27aba57c4058648a2fe0ec39451b9efc130b2f7b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:34:53.016214Z","signature_b64":"wGJWqW6SbguAQw69UmBqybijLUkeddQiSDE7nfZl3w9uW220izoCm9QZZeShZwakdGbktOqPqzmcBYz6BZQ9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05aab1984c1387012746eab27aba57c4058648a2fe0ec39451b9efc130b2f7b4","last_reissued_at":"2026-07-05T05:34:53.015786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:34:53.015786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.08810","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":"2026-07-05T05:34:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DuCJoD2fn02QQsAkuq/kheYJnONpqYTUV1Yn9SP2vb+lYJ7ZBQAUT8zb7vjlVfBbMdyjhG8vB/gCIWrFJRwHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:36:16.097611Z"},"content_sha256":"637dcb34ca1cc265dcab927f769cc46fee59b9c7c40653a8900b4ccaff635d7d","schema_version":"1.0","event_id":"sha256:637dcb34ca1cc265dcab927f769cc46fee59b9c7c40653a8900b4ccaff635d7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AWVLDGCMCODQCJ2G5KZHVOSXYQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","submitted_at":"2023-01-20T21:36:16Z","abstract_excerpt":"Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level or sup-phoneme-level and jointly trained with phonemes, making them inefficient for the downstream TTS task where only phonemes are needed. In this work, we propose a phoneme-level BERT (PL-BERT) with a pretext task of predicting the corresponding graphemes along with the regular masked phoneme predictions. Subjective evaluations show that our phoneme-level "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08810","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/2301.08810/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":"2026-07-05T05:34:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KarEKzo59ASW7/R9hpDm4rYjHZAzQOP9B0YWiU3w7ogITJ5WvHFoGv5z3lfdzB6h75fJEWR8IH3/aVwjE9nvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:36:16.098003Z"},"content_sha256":"0935c46fdef3bc43fa5981b10b950482e8312fc60d173ab925a4691eb983a53e","schema_version":"1.0","event_id":"sha256:0935c46fdef3bc43fa5981b10b950482e8312fc60d173ab925a4691eb983a53e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AWVLDGCMCODQCJ2G5KZHVOSXYQ/bundle.json","state_url":"https://pith.science/pith/AWVLDGCMCODQCJ2G5KZHVOSXYQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AWVLDGCMCODQCJ2G5KZHVOSXYQ/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":"2026-07-09T03:36:16Z","links":{"resolver":"https://pith.science/pith/AWVLDGCMCODQCJ2G5KZHVOSXYQ","bundle":"https://pith.science/pith/AWVLDGCMCODQCJ2G5KZHVOSXYQ/bundle.json","state":"https://pith.science/pith/AWVLDGCMCODQCJ2G5KZHVOSXYQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AWVLDGCMCODQCJ2G5KZHVOSXYQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AWVLDGCMCODQCJ2G5KZHVOSXYQ","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":"b4cd5efb4888780a87d987d7fb417f3e9b3859acd8137b795bba957afb3a8973","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-20T21:36:16Z","title_canon_sha256":"869b935155d74b34a5f63a0553eccb3deae6eaf5333b71da9b7e624b59c2d0d2"},"schema_version":"1.0","source":{"id":"2301.08810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08810","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08810v1","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08810","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"pith_short_12","alias_value":"AWVLDGCMCODQ","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"pith_short_16","alias_value":"AWVLDGCMCODQCJ2G","created_at":"2026-07-05T05:34:53Z"},{"alias_kind":"pith_short_8","alias_value":"AWVLDGCM","created_at":"2026-07-05T05:34:53Z"}],"graph_snapshots":[{"event_id":"sha256:0935c46fdef3bc43fa5981b10b950482e8312fc60d173ab925a4691eb983a53e","target":"graph","created_at":"2026-07-05T05:34:53Z","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/2301.08810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level or sup-phoneme-level and jointly trained with phonemes, making them inefficient for the downstream TTS task where only phonemes are needed. In this work, we propose a phoneme-level BERT (PL-BERT) with a pretext task of predicting the corresponding graphemes along with the regular masked phoneme predictions. Subjective evaluations show that our phoneme-level ","authors_text":"Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-20T21:36:16Z","title":"Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08810","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":"sha256:637dcb34ca1cc265dcab927f769cc46fee59b9c7c40653a8900b4ccaff635d7d","target":"record","created_at":"2026-07-05T05:34:53Z","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":"b4cd5efb4888780a87d987d7fb417f3e9b3859acd8137b795bba957afb3a8973","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-20T21:36:16Z","title_canon_sha256":"869b935155d74b34a5f63a0553eccb3deae6eaf5333b71da9b7e624b59c2d0d2"},"schema_version":"1.0","source":{"id":"2301.08810","kind":"arxiv","version":1}},"canonical_sha256":"05aab1984c1387012746eab27aba57c4058648a2fe0ec39451b9efc130b2f7b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05aab1984c1387012746eab27aba57c4058648a2fe0ec39451b9efc130b2f7b4","first_computed_at":"2026-07-05T05:34:53.015786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:34:53.015786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wGJWqW6SbguAQw69UmBqybijLUkeddQiSDE7nfZl3w9uW220izoCm9QZZeShZwakdGbktOqPqzmcBYz6BZQ9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:34:53.016214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.08810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:637dcb34ca1cc265dcab927f769cc46fee59b9c7c40653a8900b4ccaff635d7d","sha256:0935c46fdef3bc43fa5981b10b950482e8312fc60d173ab925a4691eb983a53e"],"state_sha256":"871d9a0cfcbd6ae8ceaa27994c1ff3f53c7e51809c2070cd03b82dad19e2c148"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PUIz/Saz6bWAcaKlNfYujwwQw5dBOylLKh4ul/BHxWTIT95BI27F485Af6pn88hK1aL2XcB82tTKlzB79rUrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:36:16.100010Z","bundle_sha256":"0fa5d6acc42c4087cd4d58c5dd9edc02b743ceefccd6d898a6cdbebf0ccbf4f7"}}