{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6WZDE63NKS6DLYAMHZYR2LTWCJ","short_pith_number":"pith:6WZDE63N","schema_version":"1.0","canonical_sha256":"f5b2327b6d54bc35e00c3e711d2e76127a704a99a78783c876e14bf7b3cee42c","source":{"kind":"arxiv","id":"2002.06758","version":2},"attestation_state":"computed","paper":{"title":"Interactive Text-to-Speech System via Joint Style Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Christian Fuegen, Qing He, Thilo Kohler, Weiyi Zheng, Yang Gao, Zhaojun Yang","submitted_at":"2020-02-17T03:35:24Z","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"},"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":"2002.06758","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2020-02-17T03:35:24Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c347d74cfa7f6ba17d8f99f10925de6044a4bfb02756db948641040db4fd0a5b","abstract_canon_sha256":"ca33c2bbc80b9a3c5e651252275418b44304c89859221d59f23a4b2e2d25234b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:06.557791Z","signature_b64":"zdQFwl7mtkhnkK4Y/8+OsWzXNzlvxDBI5/DSF01L5eyExx7orNu3IJNwRRtyavv2Uz79gpEp9owN37nT1pw4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5b2327b6d54bc35e00c3e711d2e76127a704a99a78783c876e14bf7b3cee42c","last_reissued_at":"2026-07-05T01:37:06.557353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:06.557353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Text-to-Speech System via Joint Style Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Christian Fuegen, Qing He, Thilo Kohler, Weiyi Zheng, Yang Gao, Zhaojun Yang","submitted_at":"2020-02-17T03:35:24Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06758","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/2002.06758/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":"2002.06758","created_at":"2026-07-05T01:37:06.557410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06758v2","created_at":"2026-07-05T01:37:06.557410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06758","created_at":"2026-07-05T01:37:06.557410+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WZDE63NKS6D","created_at":"2026-07-05T01:37:06.557410+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WZDE63NKS6DLYAM","created_at":"2026-07-05T01:37:06.557410+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WZDE63N","created_at":"2026-07-05T01:37:06.557410+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/6WZDE63NKS6DLYAMHZYR2LTWCJ","json":"https://pith.science/pith/6WZDE63NKS6DLYAMHZYR2LTWCJ.json","graph_json":"https://pith.science/api/pith-number/6WZDE63NKS6DLYAMHZYR2LTWCJ/graph.json","events_json":"https://pith.science/api/pith-number/6WZDE63NKS6DLYAMHZYR2LTWCJ/events.json","paper":"https://pith.science/paper/6WZDE63N"},"agent_actions":{"view_html":"https://pith.science/pith/6WZDE63NKS6DLYAMHZYR2LTWCJ","download_json":"https://pith.science/pith/6WZDE63NKS6DLYAMHZYR2LTWCJ.json","view_paper":"https://pith.science/paper/6WZDE63N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06758&json=true","fetch_graph":"https://pith.science/api/pith-number/6WZDE63NKS6DLYAMHZYR2LTWCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6WZDE63NKS6DLYAMHZYR2LTWCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WZDE63NKS6DLYAMHZYR2LTWCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WZDE63NKS6DLYAMHZYR2LTWCJ/action/storage_attestation","attest_author":"https://pith.science/pith/6WZDE63NKS6DLYAMHZYR2LTWCJ/action/author_attestation","sign_citation":"https://pith.science/pith/6WZDE63NKS6DLYAMHZYR2LTWCJ/action/citation_signature","submit_replication":"https://pith.science/pith/6WZDE63NKS6DLYAMHZYR2LTWCJ/action/replication_record"}},"created_at":"2026-07-05T01:37:06.557410+00:00","updated_at":"2026-07-05T01:37:06.557410+00:00"}