{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:C53CW5HECJLK4OHOMM43XM4GLH","short_pith_number":"pith:C53CW5HE","schema_version":"1.0","canonical_sha256":"17762b74e41256ae38ee6339bbb38659f77d1158a238784353885d2d97201014","source":{"kind":"arxiv","id":"2206.15067","version":2},"attestation_state":"computed","paper":{"title":"Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Eunwoo Song, Hoyeon Lee, Hyun-Wook Yoon, Jae-Min Kim, Min-Jae Hwang, Ohsung Kwon, Ryuichi Yamamoto","submitted_at":"2022-06-30T07:03:01Z","abstract_excerpt":"This paper proposes an effective emotional text-to-speech (TTS) system with a pre-trained language model (LM)-based emotion prediction method. Unlike conventional systems that require auxiliary inputs such as manually defined emotion classes, our system directly estimates emotion-related attributes from the input text. Specifically, we utilize generative pre-trained transformer (GPT)-3 to jointly predict both an emotion class and its strength in representing emotions coarse and fine properties, respectively. Then, these attributes are combined in the emotional embedding space and used as condi"},"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":"2206.15067","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-06-30T07:03:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0894314bed949432b8eafa2ce7e119db8310c0153f50175d9e97ee1f17beab69","abstract_canon_sha256":"373709e269303bbfb3a91226489db62ce7cda00d5d2228a1e04a9158bf11a85a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:37.839026Z","signature_b64":"UQ2q7nduak9MY9L6YxNwxMaZACKTuHPqZewUAH85qdMb23BD2R/xzw3GDByQoP7vBtxZuu9JwpOpqef+j4aTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17762b74e41256ae38ee6339bbb38659f77d1158a238784353885d2d97201014","last_reissued_at":"2026-07-05T04:36:37.838529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:37.838529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Model-Based Emotion Prediction Methods for Emotional Speech Synthesis Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Eunwoo Song, Hoyeon Lee, Hyun-Wook Yoon, Jae-Min Kim, Min-Jae Hwang, Ohsung Kwon, Ryuichi Yamamoto","submitted_at":"2022-06-30T07:03:01Z","abstract_excerpt":"This paper proposes an effective emotional text-to-speech (TTS) system with a pre-trained language model (LM)-based emotion prediction method. Unlike conventional systems that require auxiliary inputs such as manually defined emotion classes, our system directly estimates emotion-related attributes from the input text. Specifically, we utilize generative pre-trained transformer (GPT)-3 to jointly predict both an emotion class and its strength in representing emotions coarse and fine properties, respectively. Then, these attributes are combined in the emotional embedding space and used as condi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15067","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/2206.15067/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":"2206.15067","created_at":"2026-07-05T04:36:37.838589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.15067v2","created_at":"2026-07-05T04:36:37.838589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15067","created_at":"2026-07-05T04:36:37.838589+00:00"},{"alias_kind":"pith_short_12","alias_value":"C53CW5HECJLK","created_at":"2026-07-05T04:36:37.838589+00:00"},{"alias_kind":"pith_short_16","alias_value":"C53CW5HECJLK4OHO","created_at":"2026-07-05T04:36:37.838589+00:00"},{"alias_kind":"pith_short_8","alias_value":"C53CW5HE","created_at":"2026-07-05T04:36:37.838589+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.20657","citing_title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C53CW5HECJLK4OHOMM43XM4GLH","json":"https://pith.science/pith/C53CW5HECJLK4OHOMM43XM4GLH.json","graph_json":"https://pith.science/api/pith-number/C53CW5HECJLK4OHOMM43XM4GLH/graph.json","events_json":"https://pith.science/api/pith-number/C53CW5HECJLK4OHOMM43XM4GLH/events.json","paper":"https://pith.science/paper/C53CW5HE"},"agent_actions":{"view_html":"https://pith.science/pith/C53CW5HECJLK4OHOMM43XM4GLH","download_json":"https://pith.science/pith/C53CW5HECJLK4OHOMM43XM4GLH.json","view_paper":"https://pith.science/paper/C53CW5HE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.15067&json=true","fetch_graph":"https://pith.science/api/pith-number/C53CW5HECJLK4OHOMM43XM4GLH/graph.json","fetch_events":"https://pith.science/api/pith-number/C53CW5HECJLK4OHOMM43XM4GLH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C53CW5HECJLK4OHOMM43XM4GLH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C53CW5HECJLK4OHOMM43XM4GLH/action/storage_attestation","attest_author":"https://pith.science/pith/C53CW5HECJLK4OHOMM43XM4GLH/action/author_attestation","sign_citation":"https://pith.science/pith/C53CW5HECJLK4OHOMM43XM4GLH/action/citation_signature","submit_replication":"https://pith.science/pith/C53CW5HECJLK4OHOMM43XM4GLH/action/replication_record"}},"created_at":"2026-07-05T04:36:37.838589+00:00","updated_at":"2026-07-05T04:36:37.838589+00:00"}