{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7OSAVW7NVHSCX2MRW4W5OV5QS7","short_pith_number":"pith:7OSAVW7N","canonical_record":{"source":{"id":"2307.16012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-29T15:48:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1d6a7a54aa8aca850a30e387a6a9005cc420bb078bfdbd5971ba5e7861fcc738","abstract_canon_sha256":"9d95ecfc778fcac433ad9d2f22a0aced73aa02f959aa691d6c9ee1a47be0f415"},"schema_version":"1.0"},"canonical_sha256":"fba40adbeda9e42be991b72dd757b097cc1edfc61871ff05bf84ddf5901ccd26","source":{"kind":"arxiv","id":"2307.16012","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16012","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16012v1","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16012","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"7OSAVW7NVHSC","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"7OSAVW7NVHSCX2MR","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"7OSAVW7N","created_at":"2026-07-05T06:35:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7OSAVW7NVHSCX2MRW4W5OV5QS7","target":"record","payload":{"canonical_record":{"source":{"id":"2307.16012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-29T15:48:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"1d6a7a54aa8aca850a30e387a6a9005cc420bb078bfdbd5971ba5e7861fcc738","abstract_canon_sha256":"9d95ecfc778fcac433ad9d2f22a0aced73aa02f959aa691d6c9ee1a47be0f415"},"schema_version":"1.0"},"canonical_sha256":"fba40adbeda9e42be991b72dd757b097cc1edfc61871ff05bf84ddf5901ccd26","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:57.738421Z","signature_b64":"qzKlHYNWsSrBRpwEpM9B4wp53kbbKy8TV7MflqdgHP/TuOZKe0+YwupbF7BDXiWZYhaNmOtsM4hsd4ycbuWHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fba40adbeda9e42be991b72dd757b097cc1edfc61871ff05bf84ddf5901ccd26","last_reissued_at":"2026-07-05T06:35:57.737998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:57.737998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.16012","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":"2026-07-05T06:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hpFQ16QqlK1zZT+iPouWzD8Z78p0ORv7aA6mLQEWg6oXjeumULjYUbEYqnhpZvQ15pYMsiMFgZkJC8h/Gk4DDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T10:37:13.425161Z"},"content_sha256":"56f8e9a33568fabe1d20785eed7d16e61b48d281def5fb47f822367737046935","schema_version":"1.0","event_id":"sha256:56f8e9a33568fabe1d20785eed7d16e61b48d281def5fb47f822367737046935"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7OSAVW7NVHSCX2MRW4W5OV5QS7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MSStyleTTS: Multi-Scale Style Modeling with Hierarchical Context Information for Expressive Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Helen Meng, Liyang Chen, Shiyin Kang, Shun Lei, Xixin Wu, Yixuan Zhou, Zhiyong Wu","submitted_at":"2023-07-29T15:48:20Z","abstract_excerpt":"Expressive speech synthesis is crucial for many human-computer interaction scenarios, such as audiobooks, podcasts, and voice assistants. Previous works focus on predicting the style embeddings at one single scale from the information within the current sentence. Whereas, context information in neighboring sentences and multi-scale nature of style in human speech are neglected, making it challenging to convert multi-sentence text into natural and expressive speech. In this paper, we propose MSStyleTTS, a style modeling method for expressive speech synthesis, to capture and predict styles at di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16012","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/2307.16012/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":"2026-07-05T06:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"htz0mFG+/vYdIdANID7QAsaePQRr2HStntSE2mRC7DC7KYOFxDG4Co3j7dS6HCSM9C2U21WxbH1afhh7Na4sAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T10:37:13.425559Z"},"content_sha256":"94ceb253a60f770521ab69b5db1ad06007333b9c4bd4c1303e6af35e06db2a91","schema_version":"1.0","event_id":"sha256:94ceb253a60f770521ab69b5db1ad06007333b9c4bd4c1303e6af35e06db2a91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7OSAVW7NVHSCX2MRW4W5OV5QS7/bundle.json","state_url":"https://pith.science/pith/7OSAVW7NVHSCX2MRW4W5OV5QS7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7OSAVW7NVHSCX2MRW4W5OV5QS7/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":"2026-07-14T10:37:13Z","links":{"resolver":"https://pith.science/pith/7OSAVW7NVHSCX2MRW4W5OV5QS7","bundle":"https://pith.science/pith/7OSAVW7NVHSCX2MRW4W5OV5QS7/bundle.json","state":"https://pith.science/pith/7OSAVW7NVHSCX2MRW4W5OV5QS7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7OSAVW7NVHSCX2MRW4W5OV5QS7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7OSAVW7NVHSCX2MRW4W5OV5QS7","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":"9d95ecfc778fcac433ad9d2f22a0aced73aa02f959aa691d6c9ee1a47be0f415","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-29T15:48:20Z","title_canon_sha256":"1d6a7a54aa8aca850a30e387a6a9005cc420bb078bfdbd5971ba5e7861fcc738"},"schema_version":"1.0","source":{"id":"2307.16012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.16012","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.16012v1","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16012","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"7OSAVW7NVHSC","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"7OSAVW7NVHSCX2MR","created_at":"2026-07-05T06:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"7OSAVW7N","created_at":"2026-07-05T06:35:57Z"}],"graph_snapshots":[{"event_id":"sha256:94ceb253a60f770521ab69b5db1ad06007333b9c4bd4c1303e6af35e06db2a91","target":"graph","created_at":"2026-07-05T06:35:57Z","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/2307.16012/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive speech synthesis is crucial for many human-computer interaction scenarios, such as audiobooks, podcasts, and voice assistants. Previous works focus on predicting the style embeddings at one single scale from the information within the current sentence. Whereas, context information in neighboring sentences and multi-scale nature of style in human speech are neglected, making it challenging to convert multi-sentence text into natural and expressive speech. In this paper, we propose MSStyleTTS, a style modeling method for expressive speech synthesis, to capture and predict styles at di","authors_text":"Helen Meng, Liyang Chen, Shiyin Kang, Shun Lei, Xixin Wu, Yixuan Zhou, Zhiyong Wu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-29T15:48:20Z","title":"MSStyleTTS: Multi-Scale Style Modeling with Hierarchical Context Information for Expressive Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16012","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":"sha256:56f8e9a33568fabe1d20785eed7d16e61b48d281def5fb47f822367737046935","target":"record","created_at":"2026-07-05T06:35:57Z","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":"9d95ecfc778fcac433ad9d2f22a0aced73aa02f959aa691d6c9ee1a47be0f415","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-07-29T15:48:20Z","title_canon_sha256":"1d6a7a54aa8aca850a30e387a6a9005cc420bb078bfdbd5971ba5e7861fcc738"},"schema_version":"1.0","source":{"id":"2307.16012","kind":"arxiv","version":1}},"canonical_sha256":"fba40adbeda9e42be991b72dd757b097cc1edfc61871ff05bf84ddf5901ccd26","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fba40adbeda9e42be991b72dd757b097cc1edfc61871ff05bf84ddf5901ccd26","first_computed_at":"2026-07-05T06:35:57.737998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:57.737998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qzKlHYNWsSrBRpwEpM9B4wp53kbbKy8TV7MflqdgHP/TuOZKe0+YwupbF7BDXiWZYhaNmOtsM4hsd4ycbuWHCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:57.738421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.16012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56f8e9a33568fabe1d20785eed7d16e61b48d281def5fb47f822367737046935","sha256:94ceb253a60f770521ab69b5db1ad06007333b9c4bd4c1303e6af35e06db2a91"],"state_sha256":"06a60ce5e4a66ba3804dab80e8739650733b3b378cb7a15c15c89a47bcd5231e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wng5/6DYu0YD4jhOM8Q2+JYkctLJvv+5pI8lDI85GQYOfSBuIZ0AksCuYnaCk9ZHqZ0IEdkFaT6l/CiBfbEjBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T10:37:13.427764Z","bundle_sha256":"e777b4f790aad1867e078103d6c7204292ff3ec7886c210a2a718fa45c0439b8"}}