{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RFLNYZDJZ7XJQTO3XVXTY56G7R","short_pith_number":"pith:RFLNYZDJ","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"},"canonical_sha256":"8956dc6469cfee984ddbbd6f3c77c6fc4ee385ca00fd72b6732457235efd4140","source":{"kind":"arxiv","id":"2104.01408","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01408","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01408v2","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01408","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"RFLNYZDJZ7XJ","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"RFLNYZDJZ7XJQTO3","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"RFLNYZDJ","created_at":"2026-07-05T02:49:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RFLNYZDJZ7XJQTO3XVXTY56G7R","target":"record","payload":{"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"},"canonical_sha256":"8956dc6469cfee984ddbbd6f3c77c6fc4ee385ca00fd72b6732457235efd4140","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"},"source_kind":"arxiv","source_id":"2104.01408","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pLckvR9Mi+1ATJvey7Y8+u9Vj8cfgGWduw2CB9GdWkbsbX60Z/xFDj1wjSk4KlabiJd69xDrQSpEwSCNVR6rCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:10:42.789652Z"},"content_sha256":"07a5da99bd73ee174c82694bc32d3774560a751a45fa2fd0a73573d046c73845","schema_version":"1.0","event_id":"sha256:07a5da99bd73ee174c82694bc32d3774560a751a45fa2fd0a73573d046c73845"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RFLNYZDJZ7XJQTO3XVXTY56G7R","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"leeIJBu6ri3Oby++ZtWPDETUC2EkqLoomnfE4/32w+abt7HsiM1DEzxw+62f9T2Ovn8CtAT7CjemnWnjkMMDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:10:42.790149Z"},"content_sha256":"ac5067b34c5186a559e199dbd1223d60054341fce35585b70dae57ad2b2c5c05","schema_version":"1.0","event_id":"sha256:ac5067b34c5186a559e199dbd1223d60054341fce35585b70dae57ad2b2c5c05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/bundle.json","state_url":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T12:10:42Z","links":{"resolver":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R","bundle":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/bundle.json","state":"https://pith.science/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RFLNYZDJZ7XJQTO3XVXTY56G7R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RFLNYZDJZ7XJQTO3XVXTY56G7R","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":"558b0359c312121a35d26da7df979ea6fdc0895f59afe2acf5702faefae744d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T13:52:47Z","title_canon_sha256":"0cf299f53df705ec824a76250b91014dac10d667d12f0474b5f20da6ab4ce928"},"schema_version":"1.0","source":{"id":"2104.01408","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01408","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01408v2","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01408","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"RFLNYZDJZ7XJ","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"RFLNYZDJZ7XJQTO3","created_at":"2026-07-05T02:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"RFLNYZDJ","created_at":"2026-07-05T02:49:00Z"}],"graph_snapshots":[{"event_id":"sha256:ac5067b34c5186a559e199dbd1223d60054341fce35585b70dae57ad2b2c5c05","target":"graph","created_at":"2026-07-05T02:49:00Z","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/2104.01408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Berrak Sisman, Haizhou Li, Rui Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T13:52:47Z","title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01408","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":"sha256:07a5da99bd73ee174c82694bc32d3774560a751a45fa2fd0a73573d046c73845","target":"record","created_at":"2026-07-05T02:49:00Z","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":"558b0359c312121a35d26da7df979ea6fdc0895f59afe2acf5702faefae744d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-03T13:52:47Z","title_canon_sha256":"0cf299f53df705ec824a76250b91014dac10d667d12f0474b5f20da6ab4ce928"},"schema_version":"1.0","source":{"id":"2104.01408","kind":"arxiv","version":2}},"canonical_sha256":"8956dc6469cfee984ddbbd6f3c77c6fc4ee385ca00fd72b6732457235efd4140","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8956dc6469cfee984ddbbd6f3c77c6fc4ee385ca00fd72b6732457235efd4140","first_computed_at":"2026-07-05T02:49:00.594243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:00.594243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fGKYbJ/m57W0Uo6rxNhB541gwNO0EO/LfirF8m8vDjZjsiw8DK2KaeAopZX0K0RiFtJGOC0Mwqsw0B31omfnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:00.594725Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.01408","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07a5da99bd73ee174c82694bc32d3774560a751a45fa2fd0a73573d046c73845","sha256:ac5067b34c5186a559e199dbd1223d60054341fce35585b70dae57ad2b2c5c05"],"state_sha256":"847044a4914b8ad7d15b6db6aa8df3aad17193db792a0d45214993a0a8433e46"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XoAhrvMIQnCnhBcXNTK2gN7hCeEoTGdUWIwMts5BYTuj5iJPmjOAnEdAA5omrmEntDVuu9pZn6Whgf9/+skfAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:10:42.793776Z","bundle_sha256":"a5a40c007c66b223bad92be2268aac6e64f4c5ffe1d1bc98e2c197368d38ff5e"}}