{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SRR35JHZF62JFD3LQIYUR6O3UO","short_pith_number":"pith:SRR35JHZ","canonical_record":{"source":{"id":"2106.06233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-11T08:33:52Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"c1935094d142719721266cef022c3c7db48e89c6ed2f8a213d56f0bf5dd8c740","abstract_canon_sha256":"8ee52cabab10ee5803d4b8106634efced2177e565a856c2009f6da784e63be18"},"schema_version":"1.0"},"canonical_sha256":"9463bea4f92fb4928f6b823148f9dba38a5a90921a9aba20b6f7afad19a31a1c","source":{"kind":"arxiv","id":"2106.06233","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06233","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06233v2","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06233","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"SRR35JHZF62J","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"SRR35JHZF62JFD3L","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"SRR35JHZ","created_at":"2026-07-05T04:10:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SRR35JHZF62JFD3LQIYUR6O3UO","target":"record","payload":{"canonical_record":{"source":{"id":"2106.06233","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-11T08:33:52Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"c1935094d142719721266cef022c3c7db48e89c6ed2f8a213d56f0bf5dd8c740","abstract_canon_sha256":"8ee52cabab10ee5803d4b8106634efced2177e565a856c2009f6da784e63be18"},"schema_version":"1.0"},"canonical_sha256":"9463bea4f92fb4928f6b823148f9dba38a5a90921a9aba20b6f7afad19a31a1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:22.676618Z","signature_b64":"9npVJD6zq1zsfF22xR5lY/R+7ZDk5oXVfVWIdDH0Zr2pVldqKRUGXS3IwcKjTe1pBXmSwCkHGdpCkQUHeXRsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9463bea4f92fb4928f6b823148f9dba38a5a90921a9aba20b6f7afad19a31a1c","last_reissued_at":"2026-07-05T04:10:22.676117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:22.676117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.06233","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:10:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UEMrYfLyBILx0zNf2Q2e2n3tLmwQPHQSs65jnJCkKqASw8VUKD4sWeFY0Gme0gHsuoxRSKddky65jdTS1b+CAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:35:14.040369Z"},"content_sha256":"d4fa0bbe80ad1470ec240612e25ed63b6631b2df6e0fefbc100ced5c2bd3adc9","schema_version":"1.0","event_id":"sha256:d4fa0bbe80ad1470ec240612e25ed63b6631b2df6e0fefbc100ced5c2bd3adc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SRR35JHZF62JFD3LQIYUR6O3UO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Weng, Chenyi Li, Dan Su, Helen Meng, Jingbei Li, Yi Meng, Zhiyong Wu","submitted_at":"2021-06-11T08:33:52Z","abstract_excerpt":"Comparing with traditional text-to-speech (TTS) systems, conversational TTS systems are required to synthesize speeches with proper speaking style confirming to the conversational context. However, state-of-the-art context modeling methods in conversational TTS only model the textual information in context with a recurrent neural network (RNN). Such methods have limited ability in modeling the inter-speaker influence in conversations, and also neglect the speaking styles and the intra-speaker inertia inside each speaker. Inspired by DialogueGCN and its superiority in modeling such conversation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06233","kind":"arxiv","version":2},"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/2106.06233/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":"2026-07-05T04:10:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+35Zj20sDEZFqgw8aBtdF7Z1rrYxUTmhF0MkAq1DwyCjMOHVNWqupDRG5pdGTQjHT1FpcftdD8OPG/Uxrg0OCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T11:35:14.040939Z"},"content_sha256":"0c6a609fdcab573718251ea2eb76412c811d4c616620e18ef20ba716e72dba45","schema_version":"1.0","event_id":"sha256:0c6a609fdcab573718251ea2eb76412c811d4c616620e18ef20ba716e72dba45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO/bundle.json","state_url":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRR35JHZF62JFD3LQIYUR6O3UO/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":"2026-08-15T11:35:14Z","links":{"resolver":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO","bundle":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO/bundle.json","state":"https://pith.science/pith/SRR35JHZF62JFD3LQIYUR6O3UO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRR35JHZF62JFD3LQIYUR6O3UO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SRR35JHZF62JFD3LQIYUR6O3UO","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":"8ee52cabab10ee5803d4b8106634efced2177e565a856c2009f6da784e63be18","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-11T08:33:52Z","title_canon_sha256":"c1935094d142719721266cef022c3c7db48e89c6ed2f8a213d56f0bf5dd8c740"},"schema_version":"1.0","source":{"id":"2106.06233","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06233","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06233v2","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06233","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"pith_short_12","alias_value":"SRR35JHZF62J","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"pith_short_16","alias_value":"SRR35JHZF62JFD3L","created_at":"2026-07-05T04:10:22Z"},{"alias_kind":"pith_short_8","alias_value":"SRR35JHZ","created_at":"2026-07-05T04:10:22Z"}],"graph_snapshots":[{"event_id":"sha256:0c6a609fdcab573718251ea2eb76412c811d4c616620e18ef20ba716e72dba45","target":"graph","created_at":"2026-07-05T04:10:22Z","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/2106.06233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Comparing with traditional text-to-speech (TTS) systems, conversational TTS systems are required to synthesize speeches with proper speaking style confirming to the conversational context. However, state-of-the-art context modeling methods in conversational TTS only model the textual information in context with a recurrent neural network (RNN). Such methods have limited ability in modeling the inter-speaker influence in conversations, and also neglect the speaking styles and the intra-speaker inertia inside each speaker. Inspired by DialogueGCN and its superiority in modeling such conversation","authors_text":"Chao Weng, Chenyi Li, Dan Su, Helen Meng, Jingbei Li, Yi Meng, Zhiyong Wu","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-11T08:33:52Z","title":"Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-based Multi-modal Context Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06233","kind":"arxiv","version":2},"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:d4fa0bbe80ad1470ec240612e25ed63b6631b2df6e0fefbc100ced5c2bd3adc9","target":"record","created_at":"2026-07-05T04:10:22Z","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":"8ee52cabab10ee5803d4b8106634efced2177e565a856c2009f6da784e63be18","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-06-11T08:33:52Z","title_canon_sha256":"c1935094d142719721266cef022c3c7db48e89c6ed2f8a213d56f0bf5dd8c740"},"schema_version":"1.0","source":{"id":"2106.06233","kind":"arxiv","version":2}},"canonical_sha256":"9463bea4f92fb4928f6b823148f9dba38a5a90921a9aba20b6f7afad19a31a1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9463bea4f92fb4928f6b823148f9dba38a5a90921a9aba20b6f7afad19a31a1c","first_computed_at":"2026-07-05T04:10:22.676117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:10:22.676117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9npVJD6zq1zsfF22xR5lY/R+7ZDk5oXVfVWIdDH0Zr2pVldqKRUGXS3IwcKjTe1pBXmSwCkHGdpCkQUHeXRsBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:10:22.676618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06233","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4fa0bbe80ad1470ec240612e25ed63b6631b2df6e0fefbc100ced5c2bd3adc9","sha256:0c6a609fdcab573718251ea2eb76412c811d4c616620e18ef20ba716e72dba45"],"state_sha256":"55daf8476e511504487e50b6f2377a49446d66c93bf797190ed8b2ef7b2d1cbd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TkuRISCHcoEj7EhldsOMH2/uQFTd1ULXHUGQdDp3kg95qDTdBT3rPwg1xb2g3wULlVsSicWvic7M3rT/4aWABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T11:35:14.047767Z","bundle_sha256":"77f32853adf5bab35e666f5bca178a2583f3f8e64c516856b5a8324ff76c8d67"}}