{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZL2FLOYG23XR4C6LAIK4DKNNZ2","short_pith_number":"pith:ZL2FLOYG","canonical_record":{"source":{"id":"2111.04730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-11-07T08:52:04Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"a24339d56a503cadc8d874840d9b5088f06b448cbcb838e7f3e8e075c548e89e","abstract_canon_sha256":"4faf7e2ea64f351f3c217ef88be92036bc0e16c2bbe2c0572ad56f03c5f6f753"},"schema_version":"1.0"},"canonical_sha256":"caf455bb06d6ef1e0bcb0215c1a9adceb55fd0b90b8a3955e054c19bb7044005","source":{"kind":"arxiv","id":"2111.04730","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.04730","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"arxiv_version","alias_value":"2111.04730v1","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04730","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZL2FLOYG23XR","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZL2FLOYG23XR4C6L","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZL2FLOYG","created_at":"2026-07-05T03:30:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZL2FLOYG23XR4C6LAIK4DKNNZ2","target":"record","payload":{"canonical_record":{"source":{"id":"2111.04730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-11-07T08:52:04Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"a24339d56a503cadc8d874840d9b5088f06b448cbcb838e7f3e8e075c548e89e","abstract_canon_sha256":"4faf7e2ea64f351f3c217ef88be92036bc0e16c2bbe2c0572ad56f03c5f6f753"},"schema_version":"1.0"},"canonical_sha256":"caf455bb06d6ef1e0bcb0215c1a9adceb55fd0b90b8a3955e054c19bb7044005","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:18.021355Z","signature_b64":"iLgx9wrRpwgCkLH/mHvnKe8fPewjsfjRjGwmaaddVbaY2WXKYw5x5Cd2CPkKNF4+bz39HBiJ7rBmAAzX34AXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caf455bb06d6ef1e0bcb0215c1a9adceb55fd0b90b8a3955e054c19bb7044005","last_reissued_at":"2026-07-05T03:30:18.020905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:18.020905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.04730","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":"2026-07-05T03:30:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pp2UU4JZ4SVIDU2wk2CI0FLOKLXrwXowPuWUxUaiNS0Eyt59Q+jMUWgMiLRMxdSHHhL/u5IqCmnsVAzXIVBMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:40:18.856250Z"},"content_sha256":"b5908786d47acf07aaa8a358b51244066726495781c02d26fa50bc8c6b0e5eef","schema_version":"1.0","event_id":"sha256:b5908786d47acf07aaa8a358b51244066726495781c02d26fa50bc8c6b0e5eef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZL2FLOYG23XR4C6LAIK4DKNNZ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emotional Prosody Control for Speech Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Saiteja Kosgi, Sarath Sivaprasad, Vineet Gandhi","submitted_at":"2021-11-07T08:52:04Z","abstract_excerpt":"Machine-generated speech is characterized by its limited or unnatural emotional variation. Current text to speech systems generates speech with either a flat emotion, emotion selected from a predefined set, average variation learned from prosody sequences in training data or transferred from a source style. We propose a text to speech(TTS) system, where a user can choose the emotion of generated speech from a continuous and meaningful emotion space (Arousal-Valence space). The proposed TTS system can generate speech from the text in any speaker's style, with fine control of emotion. We show th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04730","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/2111.04730/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":"2026-07-05T03:30:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZvF1owJEQ903p/URsbPnxv85HdjRaWawwKPu7vo0DKcVVw6pSLxUfM2VsCteD+UnN+1X5QIm3Iu4qH6MohLFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:40:18.856980Z"},"content_sha256":"c89f819175f1c9d7e499fdb04e938f82ed785f61da76d3b80e374f5ed1a3fc54","schema_version":"1.0","event_id":"sha256:c89f819175f1c9d7e499fdb04e938f82ed785f61da76d3b80e374f5ed1a3fc54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZL2FLOYG23XR4C6LAIK4DKNNZ2/bundle.json","state_url":"https://pith.science/pith/ZL2FLOYG23XR4C6LAIK4DKNNZ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZL2FLOYG23XR4C6LAIK4DKNNZ2/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":"2026-08-03T16:40:18Z","links":{"resolver":"https://pith.science/pith/ZL2FLOYG23XR4C6LAIK4DKNNZ2","bundle":"https://pith.science/pith/ZL2FLOYG23XR4C6LAIK4DKNNZ2/bundle.json","state":"https://pith.science/pith/ZL2FLOYG23XR4C6LAIK4DKNNZ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZL2FLOYG23XR4C6LAIK4DKNNZ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZL2FLOYG23XR4C6LAIK4DKNNZ2","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":"4faf7e2ea64f351f3c217ef88be92036bc0e16c2bbe2c0572ad56f03c5f6f753","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-11-07T08:52:04Z","title_canon_sha256":"a24339d56a503cadc8d874840d9b5088f06b448cbcb838e7f3e8e075c548e89e"},"schema_version":"1.0","source":{"id":"2111.04730","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.04730","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"arxiv_version","alias_value":"2111.04730v1","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04730","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"pith_short_12","alias_value":"ZL2FLOYG23XR","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"pith_short_16","alias_value":"ZL2FLOYG23XR4C6L","created_at":"2026-07-05T03:30:18Z"},{"alias_kind":"pith_short_8","alias_value":"ZL2FLOYG","created_at":"2026-07-05T03:30:18Z"}],"graph_snapshots":[{"event_id":"sha256:c89f819175f1c9d7e499fdb04e938f82ed785f61da76d3b80e374f5ed1a3fc54","target":"graph","created_at":"2026-07-05T03:30:18Z","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/2111.04730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Machine-generated speech is characterized by its limited or unnatural emotional variation. Current text to speech systems generates speech with either a flat emotion, emotion selected from a predefined set, average variation learned from prosody sequences in training data or transferred from a source style. We propose a text to speech(TTS) system, where a user can choose the emotion of generated speech from a continuous and meaningful emotion space (Arousal-Valence space). The proposed TTS system can generate speech from the text in any speaker's style, with fine control of emotion. We show th","authors_text":"Saiteja Kosgi, Sarath Sivaprasad, Vineet Gandhi","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-11-07T08:52:04Z","title":"Emotional Prosody Control for Speech Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04730","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:b5908786d47acf07aaa8a358b51244066726495781c02d26fa50bc8c6b0e5eef","target":"record","created_at":"2026-07-05T03:30:18Z","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":"4faf7e2ea64f351f3c217ef88be92036bc0e16c2bbe2c0572ad56f03c5f6f753","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-11-07T08:52:04Z","title_canon_sha256":"a24339d56a503cadc8d874840d9b5088f06b448cbcb838e7f3e8e075c548e89e"},"schema_version":"1.0","source":{"id":"2111.04730","kind":"arxiv","version":1}},"canonical_sha256":"caf455bb06d6ef1e0bcb0215c1a9adceb55fd0b90b8a3955e054c19bb7044005","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"caf455bb06d6ef1e0bcb0215c1a9adceb55fd0b90b8a3955e054c19bb7044005","first_computed_at":"2026-07-05T03:30:18.020905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:30:18.020905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iLgx9wrRpwgCkLH/mHvnKe8fPewjsfjRjGwmaaddVbaY2WXKYw5x5Cd2CPkKNF4+bz39HBiJ7rBmAAzX34AXDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:30:18.021355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.04730","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5908786d47acf07aaa8a358b51244066726495781c02d26fa50bc8c6b0e5eef","sha256:c89f819175f1c9d7e499fdb04e938f82ed785f61da76d3b80e374f5ed1a3fc54"],"state_sha256":"30425ada42871d2cbc087928aee6a6e69f5e1051e3556fbbca9642901dba4082"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"94CENmdr3fFU/trAv9x8MSSCJOAgftzL0u8TTbdxywXvabCeS1p/9CtilfNdXb/VqaZG4CdMDCJo0RqbleHlDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:40:18.862859Z","bundle_sha256":"5e3de73eb81a4b3fc45ed3d2d1fb8b46bfb3557a7326b1982ecf02e2103a5cbd"}}