{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FD6KLVRQ2KDS7H6ZUW3EFNXVNU","short_pith_number":"pith:FD6KLVRQ","canonical_record":{"source":{"id":"2305.19709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T10:05:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"876079b18d69e015337645f5cb8e226d4c1f7dbc3b681a811be074447f0135a6","abstract_canon_sha256":"79a4c60c93efae6a2da8051b76096f9f89e235acb6c6708e97395dd04a478e26"},"schema_version":"1.0"},"canonical_sha256":"28fca5d630d2872f9fd9a5b642b6f56d0dc3e611800db2f2f57832fec99989ca","source":{"kind":"arxiv","id":"2305.19709","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19709","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19709v1","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19709","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"FD6KLVRQ2KDS","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"FD6KLVRQ2KDS7H6Z","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"FD6KLVRQ","created_at":"2026-07-05T06:15:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FD6KLVRQ2KDS7H6ZUW3EFNXVNU","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T10:05:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"876079b18d69e015337645f5cb8e226d4c1f7dbc3b681a811be074447f0135a6","abstract_canon_sha256":"79a4c60c93efae6a2da8051b76096f9f89e235acb6c6708e97395dd04a478e26"},"schema_version":"1.0"},"canonical_sha256":"28fca5d630d2872f9fd9a5b642b6f56d0dc3e611800db2f2f57832fec99989ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:54.067210Z","signature_b64":"CQPtSFjzRHT+BrXDBglClN7vx8De9oWtGZ/yFYUBkWHG90VYg7vXkUan8tIvhA2Ce4KqXk4QyGEvpjod56yyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28fca5d630d2872f9fd9a5b642b6f56d0dc3e611800db2f2f57832fec99989ca","last_reissued_at":"2026-07-05T06:15:54.066768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:54.066768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19709","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":"2026-07-05T06:15:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bU0WYRcCgvWFYMuR06PZ+lBdhl/nps5JiqSIZTLqfJf6/HPvzf79mSFg7/Qo9DTi2QwvxLgDInlSZplQy+PpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:36:05.470900Z"},"content_sha256":"d47937ca7f9b011dd9cebf0c73c28e54325b09b1a69c94740bc4f51c06905099","schema_version":"1.0","event_id":"sha256:d47937ca7f9b011dd9cebf0c73c28e54325b09b1a69c94740bc4f51c06905099"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FD6KLVRQ2KDS7H6ZUW3EFNXVNU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Dat Quoc Nguyen, Linh The Nguyen, Thinh Pham","submitted_at":"2023-05-31T10:05:33Z","abstract_excerpt":"We present XPhoneBERT, the first multilingual model pre-trained to learn phoneme representations for the downstream text-to-speech (TTS) task. Our XPhoneBERT has the same model architecture as BERT-base, trained using the RoBERTa pre-training approach on 330M phoneme-level sentences from nearly 100 languages and locales. Experimental results show that employing XPhoneBERT as an input phoneme encoder significantly boosts the performance of a strong neural TTS model in terms of naturalness and prosody and also helps produce fairly high-quality speech with limited training data. We publicly relea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19709","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/2305.19709/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":"2026-07-05T06:15:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EQjEacjGLeXOHbeCHPkBmrPqKEQeC//sKEAWXugdCx3PpZ4pOQTk11Oxihf/UvDvirUfJ+ChrDoXaJl7CmsWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:36:05.471649Z"},"content_sha256":"e83155574cd37cc672aa2c8b4b6c6b6447341ae6a3e49bbfd1624a6891b69606","schema_version":"1.0","event_id":"sha256:e83155574cd37cc672aa2c8b4b6c6b6447341ae6a3e49bbfd1624a6891b69606"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FD6KLVRQ2KDS7H6ZUW3EFNXVNU/bundle.json","state_url":"https://pith.science/pith/FD6KLVRQ2KDS7H6ZUW3EFNXVNU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FD6KLVRQ2KDS7H6ZUW3EFNXVNU/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":"2026-08-11T04:36:05Z","links":{"resolver":"https://pith.science/pith/FD6KLVRQ2KDS7H6ZUW3EFNXVNU","bundle":"https://pith.science/pith/FD6KLVRQ2KDS7H6ZUW3EFNXVNU/bundle.json","state":"https://pith.science/pith/FD6KLVRQ2KDS7H6ZUW3EFNXVNU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FD6KLVRQ2KDS7H6ZUW3EFNXVNU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FD6KLVRQ2KDS7H6ZUW3EFNXVNU","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":"79a4c60c93efae6a2da8051b76096f9f89e235acb6c6708e97395dd04a478e26","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T10:05:33Z","title_canon_sha256":"876079b18d69e015337645f5cb8e226d4c1f7dbc3b681a811be074447f0135a6"},"schema_version":"1.0","source":{"id":"2305.19709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19709","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19709v1","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19709","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"pith_short_12","alias_value":"FD6KLVRQ2KDS","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"pith_short_16","alias_value":"FD6KLVRQ2KDS7H6Z","created_at":"2026-07-05T06:15:54Z"},{"alias_kind":"pith_short_8","alias_value":"FD6KLVRQ","created_at":"2026-07-05T06:15:54Z"}],"graph_snapshots":[{"event_id":"sha256:e83155574cd37cc672aa2c8b4b6c6b6447341ae6a3e49bbfd1624a6891b69606","target":"graph","created_at":"2026-07-05T06:15:54Z","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/2305.19709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present XPhoneBERT, the first multilingual model pre-trained to learn phoneme representations for the downstream text-to-speech (TTS) task. Our XPhoneBERT has the same model architecture as BERT-base, trained using the RoBERTa pre-training approach on 330M phoneme-level sentences from nearly 100 languages and locales. Experimental results show that employing XPhoneBERT as an input phoneme encoder significantly boosts the performance of a strong neural TTS model in terms of naturalness and prosody and also helps produce fairly high-quality speech with limited training data. We publicly relea","authors_text":"Dat Quoc Nguyen, Linh The Nguyen, Thinh Pham","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T10:05:33Z","title":"XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19709","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:d47937ca7f9b011dd9cebf0c73c28e54325b09b1a69c94740bc4f51c06905099","target":"record","created_at":"2026-07-05T06:15:54Z","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":"79a4c60c93efae6a2da8051b76096f9f89e235acb6c6708e97395dd04a478e26","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-31T10:05:33Z","title_canon_sha256":"876079b18d69e015337645f5cb8e226d4c1f7dbc3b681a811be074447f0135a6"},"schema_version":"1.0","source":{"id":"2305.19709","kind":"arxiv","version":1}},"canonical_sha256":"28fca5d630d2872f9fd9a5b642b6f56d0dc3e611800db2f2f57832fec99989ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28fca5d630d2872f9fd9a5b642b6f56d0dc3e611800db2f2f57832fec99989ca","first_computed_at":"2026-07-05T06:15:54.066768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:54.066768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CQPtSFjzRHT+BrXDBglClN7vx8De9oWtGZ/yFYUBkWHG90VYg7vXkUan8tIvhA2Ce4KqXk4QyGEvpjod56yyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:54.067210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d47937ca7f9b011dd9cebf0c73c28e54325b09b1a69c94740bc4f51c06905099","sha256:e83155574cd37cc672aa2c8b4b6c6b6447341ae6a3e49bbfd1624a6891b69606"],"state_sha256":"8edbf5cdb37b0c2bbf4279976845591dbea269987852c17daa34cb677501abbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XTJJ3E8ZuYF9VMHJfQ7vaey7QP9v1WItE3IGIb++JOit1M1+cUSXfBhzuLA8wSBre7UUOkZ2pixTtbv7YtGTBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:36:05.478073Z","bundle_sha256":"817346e8724864cc526a573c7e95e5faeff4085fb6fdfd70a325e1f6f37fc49a"}}