{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5HKJENMWU4P33ES3A5E4T2RHHK","short_pith_number":"pith:5HKJENMW","canonical_record":{"source":{"id":"2307.00024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-28T19:34:16Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"0fa4b4b0fd4718da67b89deebaeeeca206aa5316a09f9b8d086aacc4a1154a9f","abstract_canon_sha256":"6716bfc70581d1f1ee7dffcacff1fd7f5b60bd5719f1f9cabbe1489fce953614"},"schema_version":"1.0"},"canonical_sha256":"e9d4923596a71fbd925b0749c9ea273a8040ec8938a19b0a8a6d6e04e1f65dd7","source":{"kind":"arxiv","id":"2307.00024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00024","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00024v1","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00024","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"pith_short_12","alias_value":"5HKJENMWU4P3","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"5HKJENMWU4P33ES3","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"5HKJENMW","created_at":"2026-07-05T06:26:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5HKJENMWU4P33ES3A5E4T2RHHK","target":"record","payload":{"canonical_record":{"source":{"id":"2307.00024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-28T19:34:16Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"0fa4b4b0fd4718da67b89deebaeeeca206aa5316a09f9b8d086aacc4a1154a9f","abstract_canon_sha256":"6716bfc70581d1f1ee7dffcacff1fd7f5b60bd5719f1f9cabbe1489fce953614"},"schema_version":"1.0"},"canonical_sha256":"e9d4923596a71fbd925b0749c9ea273a8040ec8938a19b0a8a6d6e04e1f65dd7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:34.613301Z","signature_b64":"lzQOxzYVK46tSBTFN3y/3VBMNz+YUlFYLjoCZb3s/moBcHjtCU/HPpX3dKAYjg4Z0oy51cYkOsZQkt6MsiWVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9d4923596a71fbd925b0749c9ea273a8040ec8938a19b0a8a6d6e04e1f65dd7","last_reissued_at":"2026-07-05T06:26:34.612795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:34.612795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.00024","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:26:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jndnG1tChCOo3lt6YZ3rwlkUcem1Koj3bnKe4hoWnvDyhQhp1w/nFbhngeBkgms7VBdaYwAsK6/yp5l1oEiTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:01:12.323265Z"},"content_sha256":"33f7f2d0505e5e47901f720f46a07e974984369393d6c2f7ac988d7d0cbfaf0c","schema_version":"1.0","event_id":"sha256:33f7f2d0505e5e47901f720f46a07e974984369393d6c2f7ac988d7d0cbfaf0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5HKJENMWU4P33ES3A5E4T2RHHK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Daria Diatlova, Vitaly Shutov","submitted_at":"2023-06-28T19:34:16Z","abstract_excerpt":"State-of-the-art speech synthesis models try to get as close as possible to the human voice. Hence, modelling emotions is an essential part of Text-To-Speech (TTS) research. In our work, we selected FastSpeech2 as the starting point and proposed a series of modifications for synthesizing emotional speech. According to automatic and human evaluation, our model, EmoSpeech, surpasses existing models regarding both MOS score and emotion recognition accuracy in generated speech. We provided a detailed ablation study for every extension to FastSpeech2 architecture that forms EmoSpeech. The uneven di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00024","kind":"arxiv","version":1},"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/2307.00024/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":"2026-07-05T06:26:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ggvOUQPT4NFWbinXUuPN36VGfDkN00FHBuokwxW0MRYeLVeEiS4knSLD6jqRWdWJYgOb+xhC41bj7kH8UCPKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:01:12.323786Z"},"content_sha256":"aa5338007a73c1c1bf43edc05fca70f47551f506f8f8a338b6d1fa8cd6db2c6a","schema_version":"1.0","event_id":"sha256:aa5338007a73c1c1bf43edc05fca70f47551f506f8f8a338b6d1fa8cd6db2c6a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HKJENMWU4P33ES3A5E4T2RHHK/bundle.json","state_url":"https://pith.science/pith/5HKJENMWU4P33ES3A5E4T2RHHK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HKJENMWU4P33ES3A5E4T2RHHK/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":"2026-08-09T18:01:12Z","links":{"resolver":"https://pith.science/pith/5HKJENMWU4P33ES3A5E4T2RHHK","bundle":"https://pith.science/pith/5HKJENMWU4P33ES3A5E4T2RHHK/bundle.json","state":"https://pith.science/pith/5HKJENMWU4P33ES3A5E4T2RHHK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HKJENMWU4P33ES3A5E4T2RHHK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5HKJENMWU4P33ES3A5E4T2RHHK","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":"6716bfc70581d1f1ee7dffcacff1fd7f5b60bd5719f1f9cabbe1489fce953614","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-28T19:34:16Z","title_canon_sha256":"0fa4b4b0fd4718da67b89deebaeeeca206aa5316a09f9b8d086aacc4a1154a9f"},"schema_version":"1.0","source":{"id":"2307.00024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.00024","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"arxiv_version","alias_value":"2307.00024v1","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.00024","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"pith_short_12","alias_value":"5HKJENMWU4P3","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"5HKJENMWU4P33ES3","created_at":"2026-07-05T06:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"5HKJENMW","created_at":"2026-07-05T06:26:34Z"}],"graph_snapshots":[{"event_id":"sha256:aa5338007a73c1c1bf43edc05fca70f47551f506f8f8a338b6d1fa8cd6db2c6a","target":"graph","created_at":"2026-07-05T06:26:34Z","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/2307.00024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art speech synthesis models try to get as close as possible to the human voice. Hence, modelling emotions is an essential part of Text-To-Speech (TTS) research. In our work, we selected FastSpeech2 as the starting point and proposed a series of modifications for synthesizing emotional speech. According to automatic and human evaluation, our model, EmoSpeech, surpasses existing models regarding both MOS score and emotion recognition accuracy in generated speech. We provided a detailed ablation study for every extension to FastSpeech2 architecture that forms EmoSpeech. The uneven di","authors_text":"Daria Diatlova, Vitaly Shutov","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-28T19:34:16Z","title":"EmoSpeech: Guiding FastSpeech2 Towards Emotional Text to Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.00024","kind":"arxiv","version":1},"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":"sha256:33f7f2d0505e5e47901f720f46a07e974984369393d6c2f7ac988d7d0cbfaf0c","target":"record","created_at":"2026-07-05T06:26:34Z","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":"6716bfc70581d1f1ee7dffcacff1fd7f5b60bd5719f1f9cabbe1489fce953614","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-06-28T19:34:16Z","title_canon_sha256":"0fa4b4b0fd4718da67b89deebaeeeca206aa5316a09f9b8d086aacc4a1154a9f"},"schema_version":"1.0","source":{"id":"2307.00024","kind":"arxiv","version":1}},"canonical_sha256":"e9d4923596a71fbd925b0749c9ea273a8040ec8938a19b0a8a6d6e04e1f65dd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9d4923596a71fbd925b0749c9ea273a8040ec8938a19b0a8a6d6e04e1f65dd7","first_computed_at":"2026-07-05T06:26:34.612795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:34.612795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lzQOxzYVK46tSBTFN3y/3VBMNz+YUlFYLjoCZb3s/moBcHjtCU/HPpX3dKAYjg4Z0oy51cYkOsZQkt6MsiWVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:34.613301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.00024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33f7f2d0505e5e47901f720f46a07e974984369393d6c2f7ac988d7d0cbfaf0c","sha256:aa5338007a73c1c1bf43edc05fca70f47551f506f8f8a338b6d1fa8cd6db2c6a"],"state_sha256":"ff4ec74d7b1143f9996b7d149566b17151506f16769db84e7289ac5dce6fcda7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GsZ0qkfW0Lyyul+AmvcJ7Qf03Q1QaSVEY9kx7WzpJVvzscsq6vGwSqjSbRk5+d3Y0R088Nh8PrgvDZliA19ZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:01:12.328078Z","bundle_sha256":"37547a97cdd7d896d238bd6210f06fcb507619d481f60d2280d3e61dfaecd1eb"}}