{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6WZDE63NKS6DLYAMHZYR2LTWCJ","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":"ca33c2bbc80b9a3c5e651252275418b44304c89859221d59f23a4b2e2d25234b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-02-17T03:35:24Z","title_canon_sha256":"c347d74cfa7f6ba17d8f99f10925de6044a4bfb02756db948641040db4fd0a5b"},"schema_version":"1.0","source":{"id":"2002.06758","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06758","created_at":"2026-07-05T01:37:06Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06758v2","created_at":"2026-07-05T01:37:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06758","created_at":"2026-07-05T01:37:06Z"},{"alias_kind":"pith_short_12","alias_value":"6WZDE63NKS6D","created_at":"2026-07-05T01:37:06Z"},{"alias_kind":"pith_short_16","alias_value":"6WZDE63NKS6DLYAM","created_at":"2026-07-05T01:37:06Z"},{"alias_kind":"pith_short_8","alias_value":"6WZDE63N","created_at":"2026-07-05T01:37:06Z"}],"graph_snapshots":[{"event_id":"sha256:2f189e9de625347c634448c5e50abffa711753644a4b9a850fa6b527979a57a2","target":"graph","created_at":"2026-07-05T01:37:06Z","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/2002.06758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While modern TTS technologies have made significant advancements in audio quality, there is still a lack of behavior naturalness compared to conversing with people. We propose a style-embedded TTS system that generates styled responses based on the speech query style. To achieve this, the system includes a style extraction model that extracts a style embedding from the speech query, which is then used by the TTS to produce a matching response. We faced two main challenges: 1) only a small portion of the TTS training dataset has style labels, which is needed to train a multi-style TTS that resp","authors_text":"Christian Fuegen, Qing He, Thilo Kohler, Weiyi Zheng, Yang Gao, Zhaojun Yang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-02-17T03:35:24Z","title":"Interactive Text-to-Speech System via Joint Style Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06758","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":"sha256:6bed0ae3e198d89c8b46569bfdc6122194d5c888b894aa082b4e5846f664a42e","target":"record","created_at":"2026-07-05T01:37:06Z","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":"ca33c2bbc80b9a3c5e651252275418b44304c89859221d59f23a4b2e2d25234b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-02-17T03:35:24Z","title_canon_sha256":"c347d74cfa7f6ba17d8f99f10925de6044a4bfb02756db948641040db4fd0a5b"},"schema_version":"1.0","source":{"id":"2002.06758","kind":"arxiv","version":2}},"canonical_sha256":"f5b2327b6d54bc35e00c3e711d2e76127a704a99a78783c876e14bf7b3cee42c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5b2327b6d54bc35e00c3e711d2e76127a704a99a78783c876e14bf7b3cee42c","first_computed_at":"2026-07-05T01:37:06.557353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:37:06.557353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zdQFwl7mtkhnkK4Y/8+OsWzXNzlvxDBI5/DSF01L5eyExx7orNu3IJNwRRtyavv2Uz79gpEp9owN37nT1pw4DA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:37:06.557791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06758","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bed0ae3e198d89c8b46569bfdc6122194d5c888b894aa082b4e5846f664a42e","sha256:2f189e9de625347c634448c5e50abffa711753644a4b9a850fa6b527979a57a2"],"state_sha256":"58f8a511e4c82c739f5b5f580e94a3f25528417eae726514e1978fa56f4fb5e6"}