{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:W5TC3G7NR6ZXDUBILIOP6FAOYS","short_pith_number":"pith:W5TC3G7N","schema_version":"1.0","canonical_sha256":"b7662d9bed8fb371d0285a1cff140ec48d486513da87e8e4bb34f4537e1c70f4","source":{"kind":"arxiv","id":"2104.00436","version":2},"attestation_state":"computed","paper":{"title":"Expressive Text-to-Speech using Style Tag","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Jong Jin Kim, Minchan Kim, Nam Soo Kim, Sung Jun Cheon","submitted_at":"2021-04-01T12:40:07Z","abstract_excerpt":"As recent text-to-speech (TTS) systems have been rapidly improved in speech quality and generation speed, many researchers now focus on a more challenging issue: expressive TTS. To control speaking styles, existing expressive TTS models use categorical style index or reference speech as style input. In this work, we propose StyleTagging-TTS (ST-TTS), a novel expressive TTS model that utilizes a style tag written in natural language. Using a style-tagged TTS dataset and a pre-trained language model, we modeled the relationship between linguistic embedding and speaking style domain, which enable"},"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":"2104.00436","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-01T12:40:07Z","cross_cats_sorted":[],"title_canon_sha256":"831791d120cb2c9b5a55e9f3fdb25ae454db22db3669cace6671f949f074880b","abstract_canon_sha256":"5c4c81c40436a72766934f586bbab3fc232390b18a8e9a1978cee8f8a844468e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:49.050181Z","signature_b64":"dhpCW4H8StIRoptcSzBebqON1Ku+rfgF8sRip79Xkv/QNdbE9gwj7gO4ZmwxvhFAlVJR/re+fa/lOj6W2QIdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7662d9bed8fb371d0285a1cff140ec48d486513da87e8e4bb34f4537e1c70f4","last_reissued_at":"2026-07-05T05:03:49.049779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:49.049779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expressive Text-to-Speech using Style Tag","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Byoung Jin Choi, Jong Jin Kim, Minchan Kim, Nam Soo Kim, Sung Jun Cheon","submitted_at":"2021-04-01T12:40:07Z","abstract_excerpt":"As recent text-to-speech (TTS) systems have been rapidly improved in speech quality and generation speed, many researchers now focus on a more challenging issue: expressive TTS. To control speaking styles, existing expressive TTS models use categorical style index or reference speech as style input. In this work, we propose StyleTagging-TTS (ST-TTS), a novel expressive TTS model that utilizes a style tag written in natural language. Using a style-tagged TTS dataset and a pre-trained language model, we modeled the relationship between linguistic embedding and speaking style domain, which enable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00436","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/2104.00436/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":"2104.00436","created_at":"2026-07-05T05:03:49.049836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00436v2","created_at":"2026-07-05T05:03:49.049836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00436","created_at":"2026-07-05T05:03:49.049836+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5TC3G7NR6ZX","created_at":"2026-07-05T05:03:49.049836+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5TC3G7NR6ZXDUBI","created_at":"2026-07-05T05:03:49.049836+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5TC3G7N","created_at":"2026-07-05T05:03:49.049836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02742","citing_title":"Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS","json":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS.json","graph_json":"https://pith.science/api/pith-number/W5TC3G7NR6ZXDUBILIOP6FAOYS/graph.json","events_json":"https://pith.science/api/pith-number/W5TC3G7NR6ZXDUBILIOP6FAOYS/events.json","paper":"https://pith.science/paper/W5TC3G7N"},"agent_actions":{"view_html":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS","download_json":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS.json","view_paper":"https://pith.science/paper/W5TC3G7N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00436&json=true","fetch_graph":"https://pith.science/api/pith-number/W5TC3G7NR6ZXDUBILIOP6FAOYS/graph.json","fetch_events":"https://pith.science/api/pith-number/W5TC3G7NR6ZXDUBILIOP6FAOYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/action/storage_attestation","attest_author":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/action/author_attestation","sign_citation":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/action/citation_signature","submit_replication":"https://pith.science/pith/W5TC3G7NR6ZXDUBILIOP6FAOYS/action/replication_record"}},"created_at":"2026-07-05T05:03:49.049836+00:00","updated_at":"2026-07-05T05:03:49.049836+00:00"}