{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:M6R2EOYFBGXWYNA4NMCSDJNG3I","short_pith_number":"pith:M6R2EOYF","canonical_record":{"source":{"id":"2211.14548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-26T12:06:21Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"ba5b234d4ebb3865377d5f5dd3356ad108134d41701ac2448c1b620dbde36136","abstract_canon_sha256":"cc86d83e8567b63b5b8d31c275223f906c977d94de1514118a9f165d8183e906"},"schema_version":"1.0"},"canonical_sha256":"67a3a23b0509af6c341c6b0521a5a6da00312aad5976541376e7cac6e5245921","source":{"kind":"arxiv","id":"2211.14548","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.14548","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"arxiv_version","alias_value":"2211.14548v1","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14548","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"pith_short_12","alias_value":"M6R2EOYFBGXW","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"pith_short_16","alias_value":"M6R2EOYFBGXWYNA4","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"pith_short_8","alias_value":"M6R2EOYF","created_at":"2026-07-05T05:19:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:M6R2EOYFBGXWYNA4NMCSDJNG3I","target":"record","payload":{"canonical_record":{"source":{"id":"2211.14548","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-26T12:06:21Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"ba5b234d4ebb3865377d5f5dd3356ad108134d41701ac2448c1b620dbde36136","abstract_canon_sha256":"cc86d83e8567b63b5b8d31c275223f906c977d94de1514118a9f165d8183e906"},"schema_version":"1.0"},"canonical_sha256":"67a3a23b0509af6c341c6b0521a5a6da00312aad5976541376e7cac6e5245921","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:41.089708Z","signature_b64":"yYkQ4BHBbhcGXOX4UNFxmafzn1y/1/WzGV8kif+q8Al+5qsxtF5FstvoHRMtoCRx5ZJ62gsrP9SqSmvvt4VkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67a3a23b0509af6c341c6b0521a5a6da00312aad5976541376e7cac6e5245921","last_reissued_at":"2026-07-05T05:19:41.089220Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:41.089220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.14548","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":"2026-07-05T05:19:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PCrKTo3sz5/rcyZupQEb0n/IxBiwmK/yZrfcD/3x4Yb4NVbrVLDnUZVeF/L/DgwGJmVS/w161cw+/wLsxIqzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:17:00.578128Z"},"content_sha256":"d646e4f073bb8b68f7a9255758ffa3104658fcaee78dac31a5abe5852ddd64f9","schema_version":"1.0","event_id":"sha256:d646e4f073bb8b68f7a9255758ffa3104658fcaee78dac31a5abe5852ddd64f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:M6R2EOYFBGXWYNA4NMCSDJNG3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Expressive Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM"],"primary_cat":"eess.AS","authors_text":"Chang Zhou, Jianhong Tu, Ju Fan, Kai Hu, Siqi Zheng, Xiaohuan Zhou, Zeyu Cui","submitted_at":"2022-11-26T12:06:21Z","abstract_excerpt":"The goal of expressive Text-to-speech (TTS) is to synthesize natural speech with desired content, prosody, emotion, or timbre, in high expressiveness. Most of previous studies attempt to generate speech from given labels of styles and emotions, which over-simplifies the problem by classifying styles and emotions into a fixed number of pre-defined categories. In this paper, we introduce a new task setting, Contextual TTS (CTTS). The main idea of CTTS is that how a person speaks depends on the particular context she is in, where the context can typically be represented as text. Thus, in the CTTS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14548","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/2211.14548/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":"2026-07-05T05:19:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v/MLKUC6aMaHkyXXseCFqvzqylwhOtiPG167idiIatubSUV7LqAzeynszHFTsK7BqgzCmjD4qg9wb9L8y5vBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:17:00.578611Z"},"content_sha256":"f2233da93c4d557478a7d792f360f8a70544b2aa00640aec727fb7f08390b875","schema_version":"1.0","event_id":"sha256:f2233da93c4d557478a7d792f360f8a70544b2aa00640aec727fb7f08390b875"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6R2EOYFBGXWYNA4NMCSDJNG3I/bundle.json","state_url":"https://pith.science/pith/M6R2EOYFBGXWYNA4NMCSDJNG3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6R2EOYFBGXWYNA4NMCSDJNG3I/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":"2026-08-04T09:17:00Z","links":{"resolver":"https://pith.science/pith/M6R2EOYFBGXWYNA4NMCSDJNG3I","bundle":"https://pith.science/pith/M6R2EOYFBGXWYNA4NMCSDJNG3I/bundle.json","state":"https://pith.science/pith/M6R2EOYFBGXWYNA4NMCSDJNG3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6R2EOYFBGXWYNA4NMCSDJNG3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:M6R2EOYFBGXWYNA4NMCSDJNG3I","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":"cc86d83e8567b63b5b8d31c275223f906c977d94de1514118a9f165d8183e906","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-26T12:06:21Z","title_canon_sha256":"ba5b234d4ebb3865377d5f5dd3356ad108134d41701ac2448c1b620dbde36136"},"schema_version":"1.0","source":{"id":"2211.14548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.14548","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"arxiv_version","alias_value":"2211.14548v1","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14548","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"pith_short_12","alias_value":"M6R2EOYFBGXW","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"pith_short_16","alias_value":"M6R2EOYFBGXWYNA4","created_at":"2026-07-05T05:19:41Z"},{"alias_kind":"pith_short_8","alias_value":"M6R2EOYF","created_at":"2026-07-05T05:19:41Z"}],"graph_snapshots":[{"event_id":"sha256:f2233da93c4d557478a7d792f360f8a70544b2aa00640aec727fb7f08390b875","target":"graph","created_at":"2026-07-05T05:19:41Z","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/2211.14548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of expressive Text-to-speech (TTS) is to synthesize natural speech with desired content, prosody, emotion, or timbre, in high expressiveness. Most of previous studies attempt to generate speech from given labels of styles and emotions, which over-simplifies the problem by classifying styles and emotions into a fixed number of pre-defined categories. In this paper, we introduce a new task setting, Contextual TTS (CTTS). The main idea of CTTS is that how a person speaks depends on the particular context she is in, where the context can typically be represented as text. Thus, in the CTTS","authors_text":"Chang Zhou, Jianhong Tu, Ju Fan, Kai Hu, Siqi Zheng, Xiaohuan Zhou, Zeyu Cui","cross_cats":["cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-26T12:06:21Z","title":"Contextual Expressive Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14548","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:d646e4f073bb8b68f7a9255758ffa3104658fcaee78dac31a5abe5852ddd64f9","target":"record","created_at":"2026-07-05T05:19:41Z","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":"cc86d83e8567b63b5b8d31c275223f906c977d94de1514118a9f165d8183e906","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-26T12:06:21Z","title_canon_sha256":"ba5b234d4ebb3865377d5f5dd3356ad108134d41701ac2448c1b620dbde36136"},"schema_version":"1.0","source":{"id":"2211.14548","kind":"arxiv","version":1}},"canonical_sha256":"67a3a23b0509af6c341c6b0521a5a6da00312aad5976541376e7cac6e5245921","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67a3a23b0509af6c341c6b0521a5a6da00312aad5976541376e7cac6e5245921","first_computed_at":"2026-07-05T05:19:41.089220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:41.089220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yYkQ4BHBbhcGXOX4UNFxmafzn1y/1/WzGV8kif+q8Al+5qsxtF5FstvoHRMtoCRx5ZJ62gsrP9SqSmvvt4VkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:41.089708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.14548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d646e4f073bb8b68f7a9255758ffa3104658fcaee78dac31a5abe5852ddd64f9","sha256:f2233da93c4d557478a7d792f360f8a70544b2aa00640aec727fb7f08390b875"],"state_sha256":"4fc513aa857c4d5cc8ea830169778172263fe765267902225e0e03d260eb9fde"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KEkYXSxhM7kcJj/EMC/CDsp6DwfyLk1zdXhFQv4wqjlybdl/sFll67pjDrUBxv9V1zTkpchV+UgEACW8Ule6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:17:00.581987Z","bundle_sha256":"ff5b53c753dac9347991d70469cd75faac934bc50d2f6c0f89bfffcfbc6b2153"}}