{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RFLNYZDJZ7XJQTO3XVXTY56G7R","short_pith_number":"pith:RFLNYZDJ","schema_version":"1.0","canonical_sha256":"8956dc6469cfee984ddbbd6f3c77c6fc4ee385ca00fd72b6732457235efd4140","source":{"kind":"arxiv","id":"2104.01408","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Berrak Sisman, Haizhou Li, Rui Liu","submitted_at":"2021-04-03T13:52:47Z","abstract_excerpt":"Emotional text-to-speech synthesis (ETTS) has seen much progress in recent years. However, the generated voice is often not perceptually identifiable by its intended emotion category. To address this problem, we propose a new interactive training paradigm for ETTS, denoted as i-ETTS, which seeks to directly improve the emotion discriminability by interacting with a speech emotion recognition (SER) model. Moreover, we formulate an iterative training strategy with reinforcement learning to ensure the quality of i-ETTS optimization. Experimental results demonstrate that the proposed i-ETTS outper"},"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":"2104.01408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T13:52:47Z","cross_cats_sorted":[],"title_canon_sha256":"0cf299f53df705ec824a76250b91014dac10d667d12f0474b5f20da6ab4ce928","abstract_canon_sha256":"558b0359c312121a35d26da7df979ea6fdc0895f59afe2acf5702faefae744d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:00.594725Z","signature_b64":"fGKYbJ/m57W0Uo6rxNhB541gwNO0EO/LfirF8m8vDjZjsiw8DK2KaeAopZX0K0RiFtJGOC0Mwqsw0B31omfnBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8956dc6469cfee984ddbbd6f3c77c6fc4ee385ca00fd72b6732457235efd4140","last_reissued_at":"2026-07-05T02:49:00.594243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:00.594243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Berrak Sisman, Haizhou Li, Rui Liu","submitted_at":"2021-04-03T13:52:47Z","abstract_excerpt":"Emotional text-to-speech synthesis (ETTS) has seen much progress in recent years. However, the generated voice is often not perceptually identifiable by its intended emotion category. To address this problem, we propose a new interactive training paradigm for ETTS, denoted as i-ETTS, which seeks to directly improve the emotion discriminability by interacting with a speech emotion recognition (SER) model. Moreover, we formulate an iterative training strategy with reinforcement learning to ensure the quality of i-ETTS optimization. Experimental results demonstrate that the proposed i-ETTS outper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01408","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/2104.01408/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":"2104.01408","created_at":"2026-07-05T02:49:00.594301+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.01408v2","created_at":"2026-07-05T02:49:00.594301+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01408","created_at":"2026-07-05T02:49:00.594301+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFLNYZDJZ7XJ","created_at":"2026-07-05T02:49:00.594301+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFLNYZDJZ7XJQTO3","created_at":"2026-07-05T02:49:00.594301+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFLNYZDJ","created_at":"2026-07-05T02:49:00.594301+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":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R","json":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R.json","graph_json":"https://pith.science/api/pith-number/RFLNYZDJZ7XJQTO3XVXTY56G7R/graph.json","events_json":"https://pith.science/api/pith-number/RFLNYZDJZ7XJQTO3XVXTY56G7R/events.json","paper":"https://pith.science/paper/RFLNYZDJ"},"agent_actions":{"view_html":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R","download_json":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R.json","view_paper":"https://pith.science/paper/RFLNYZDJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.01408&json=true","fetch_graph":"https://pith.science/api/pith-number/RFLNYZDJZ7XJQTO3XVXTY56G7R/graph.json","fetch_events":"https://pith.science/api/pith-number/RFLNYZDJZ7XJQTO3XVXTY56G7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/action/storage_attestation","attest_author":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/action/author_attestation","sign_citation":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/action/citation_signature","submit_replication":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/action/replication_record"}},"created_at":"2026-07-05T02:49:00.594301+00:00","updated_at":"2026-07-05T02:49:00.594301+00:00"}