{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DLJR7QYCUCVMWSRE2K2MHOQSSM","short_pith_number":"pith:DLJR7QYC","schema_version":"1.0","canonical_sha256":"1ad31fc302a0aacb4a24d2b4c3ba12933f5f73de93f9fe0aa3c2823423121ec8","source":{"kind":"arxiv","id":"2304.06359","version":1},"attestation_state":"computed","paper":{"title":"Context-aware Coherent Speaking Style Prediction with Hierarchical Transformers for Audiobook 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, Yixuan Zhou, Zhiyong Wu","submitted_at":"2023-04-13T09:26:04Z","abstract_excerpt":"Recent advances in text-to-speech have significantly improved the expressiveness of synthesized speech. However, it is still challenging to generate speech with contextually appropriate and coherent speaking style for multi-sentence text in audiobooks. In this paper, we propose a context-aware coherent speaking style prediction method for audiobook speech synthesis. To predict the style embedding of the current utterance, a hierarchical transformer-based context-aware style predictor with a mixture attention mask is designed, considering both text-side context information and speech-side style"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2304.06359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-04-13T09:26:04Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"01a022e281c90f5bdbd651d1618e6e74feb08ec38e80e09b5105f147a63558a2","abstract_canon_sha256":"4a4874656ecc1a090a56514210d43b2a9103e36a321bb66d36b4e1e2bc89e478"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:42.606047Z","signature_b64":"+eobMyY0MJfFFOD4iRhOlrrg1z6PIcaVzSglSLuadLmJgC8vlYj8YCCTME6KWqJY0+v7ZvK+3YqrgCxMQiIrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ad31fc302a0aacb4a24d2b4c3ba12933f5f73de93f9fe0aa3c2823423121ec8","last_reissued_at":"2026-07-05T06:00:42.605542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:42.605542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-aware Coherent Speaking Style Prediction with Hierarchical Transformers for Audiobook 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, Yixuan Zhou, Zhiyong Wu","submitted_at":"2023-04-13T09:26:04Z","abstract_excerpt":"Recent advances in text-to-speech have significantly improved the expressiveness of synthesized speech. However, it is still challenging to generate speech with contextually appropriate and coherent speaking style for multi-sentence text in audiobooks. In this paper, we propose a context-aware coherent speaking style prediction method for audiobook speech synthesis. To predict the style embedding of the current utterance, a hierarchical transformer-based context-aware style predictor with a mixture attention mask is designed, considering both text-side context information and speech-side style"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06359","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/2304.06359/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2304.06359","created_at":"2026-07-05T06:00:42.605604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06359v1","created_at":"2026-07-05T06:00:42.605604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06359","created_at":"2026-07-05T06:00:42.605604+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLJR7QYCUCVM","created_at":"2026-07-05T06:00:42.605604+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLJR7QYCUCVMWSRE","created_at":"2026-07-05T06:00:42.605604+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLJR7QYC","created_at":"2026-07-05T06:00:42.605604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DLJR7QYCUCVMWSRE2K2MHOQSSM","json":"https://pith.science/pith/DLJR7QYCUCVMWSRE2K2MHOQSSM.json","graph_json":"https://pith.science/api/pith-number/DLJR7QYCUCVMWSRE2K2MHOQSSM/graph.json","events_json":"https://pith.science/api/pith-number/DLJR7QYCUCVMWSRE2K2MHOQSSM/events.json","paper":"https://pith.science/paper/DLJR7QYC"},"agent_actions":{"view_html":"https://pith.science/pith/DLJR7QYCUCVMWSRE2K2MHOQSSM","download_json":"https://pith.science/pith/DLJR7QYCUCVMWSRE2K2MHOQSSM.json","view_paper":"https://pith.science/paper/DLJR7QYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06359&json=true","fetch_graph":"https://pith.science/api/pith-number/DLJR7QYCUCVMWSRE2K2MHOQSSM/graph.json","fetch_events":"https://pith.science/api/pith-number/DLJR7QYCUCVMWSRE2K2MHOQSSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLJR7QYCUCVMWSRE2K2MHOQSSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLJR7QYCUCVMWSRE2K2MHOQSSM/action/storage_attestation","attest_author":"https://pith.science/pith/DLJR7QYCUCVMWSRE2K2MHOQSSM/action/author_attestation","sign_citation":"https://pith.science/pith/DLJR7QYCUCVMWSRE2K2MHOQSSM/action/citation_signature","submit_replication":"https://pith.science/pith/DLJR7QYCUCVMWSRE2K2MHOQSSM/action/replication_record"}},"created_at":"2026-07-05T06:00:42.605604+00:00","updated_at":"2026-07-05T06:00:42.605604+00:00"}