{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:I6TOG52JGGWVB2TAEM2CXAR4NE","short_pith_number":"pith:I6TOG52J","canonical_record":{"source":{"id":"2105.13086","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-27T12:16:42Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7993f5170d3647ba3f03e028943f4ab0463cdac59610b70091f76a2e63255045","abstract_canon_sha256":"ea4811f4b8205df6a52b9b9cda582b268dc3166fc7e996bc6290f2dcb2599bdd"},"schema_version":"1.0"},"canonical_sha256":"47a6e3774931ad50ea6023342b823c690fb2ccfb9dbb49fa8fb1732a563713b0","source":{"kind":"arxiv","id":"2105.13086","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13086","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13086v3","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13086","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"pith_short_12","alias_value":"I6TOG52JGGWV","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"I6TOG52JGGWVB2TA","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"I6TOG52J","created_at":"2026-07-05T09:27:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:I6TOG52JGGWVB2TAEM2CXAR4NE","target":"record","payload":{"canonical_record":{"source":{"id":"2105.13086","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-27T12:16:42Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"7993f5170d3647ba3f03e028943f4ab0463cdac59610b70091f76a2e63255045","abstract_canon_sha256":"ea4811f4b8205df6a52b9b9cda582b268dc3166fc7e996bc6290f2dcb2599bdd"},"schema_version":"1.0"},"canonical_sha256":"47a6e3774931ad50ea6023342b823c690fb2ccfb9dbb49fa8fb1732a563713b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:18.114194Z","signature_b64":"sYgiD0vuHnoVO3qB5B6hNpYE4BBf4jJrI3N9gWRX6tRK5aZ98Z6SvyvPIOwnv41wPq5BmE1kF3VRMxGzN6a/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47a6e3774931ad50ea6023342b823c690fb2ccfb9dbb49fa8fb1732a563713b0","last_reissued_at":"2026-07-05T09:27:18.113766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:18.113766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.13086","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:27:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9b7WofnRiwH3iMMDlPoNVUZmonNkGph1r4qlXkcFtDhY+P5fXZkdquhO3QhEvrT6ZCEh2ahviWL6L8m315LAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T17:51:32.704982Z"},"content_sha256":"0ee25bef7352a6994ae1f7e1bddc2ba4769afc62ee3b62d68046688f1e89c83a","schema_version":"1.0","event_id":"sha256:0ee25bef7352a6994ae1f7e1bddc2ba4769afc62ee3b62d68046688f1e89c83a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:I6TOG52JGGWVB2TAEM2CXAR4NE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phone-Level Prosody Modelling with GMM-Based MDN for Diverse and Controllable Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenpeng Du, Kai Yu","submitted_at":"2021-05-27T12:16:42Z","abstract_excerpt":"Generating natural speech with a diverse and smooth prosody pattern is a challenging task. Although random sampling with phone-level prosody distribution has been investigated to generate different prosody patterns, the diversity of the generated speech is still very limited and far from what can be achieved by humans. This is largely due to the use of uni-modal distribution, such as single Gaussian, in the prior works of phone-level prosody modelling. In this work, we propose a novel approach that models phone-level prosodies with a GMM-based mixture density network(MDN) and then extend it fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13086","kind":"arxiv","version":3},"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/2105.13086/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":"2026-07-05T09:27:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cKs5yGkmMP8m7xS6giajublrbe6yXDE3R/PoHnro6Shjzeolq6EYxWyl2USAixnLBR9mEV4TsPlSU3sooKKiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T17:51:32.705384Z"},"content_sha256":"1a00de8519908620ffe4cce97d51af65275546edfe089b502d8ad1433d7ecc1c","schema_version":"1.0","event_id":"sha256:1a00de8519908620ffe4cce97d51af65275546edfe089b502d8ad1433d7ecc1c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I6TOG52JGGWVB2TAEM2CXAR4NE/bundle.json","state_url":"https://pith.science/pith/I6TOG52JGGWVB2TAEM2CXAR4NE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I6TOG52JGGWVB2TAEM2CXAR4NE/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":"2026-07-11T17:51:32Z","links":{"resolver":"https://pith.science/pith/I6TOG52JGGWVB2TAEM2CXAR4NE","bundle":"https://pith.science/pith/I6TOG52JGGWVB2TAEM2CXAR4NE/bundle.json","state":"https://pith.science/pith/I6TOG52JGGWVB2TAEM2CXAR4NE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I6TOG52JGGWVB2TAEM2CXAR4NE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:I6TOG52JGGWVB2TAEM2CXAR4NE","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":"ea4811f4b8205df6a52b9b9cda582b268dc3166fc7e996bc6290f2dcb2599bdd","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-27T12:16:42Z","title_canon_sha256":"7993f5170d3647ba3f03e028943f4ab0463cdac59610b70091f76a2e63255045"},"schema_version":"1.0","source":{"id":"2105.13086","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.13086","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"arxiv_version","alias_value":"2105.13086v3","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.13086","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"pith_short_12","alias_value":"I6TOG52JGGWV","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"I6TOG52JGGWVB2TA","created_at":"2026-07-05T09:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"I6TOG52J","created_at":"2026-07-05T09:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:1a00de8519908620ffe4cce97d51af65275546edfe089b502d8ad1433d7ecc1c","target":"graph","created_at":"2026-07-05T09:27:18Z","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/2105.13086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating natural speech with a diverse and smooth prosody pattern is a challenging task. Although random sampling with phone-level prosody distribution has been investigated to generate different prosody patterns, the diversity of the generated speech is still very limited and far from what can be achieved by humans. This is largely due to the use of uni-modal distribution, such as single Gaussian, in the prior works of phone-level prosody modelling. In this work, we propose a novel approach that models phone-level prosodies with a GMM-based mixture density network(MDN) and then extend it fo","authors_text":"Chenpeng Du, Kai Yu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-27T12:16:42Z","title":"Phone-Level Prosody Modelling with GMM-Based MDN for Diverse and Controllable Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.13086","kind":"arxiv","version":3},"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":"sha256:0ee25bef7352a6994ae1f7e1bddc2ba4769afc62ee3b62d68046688f1e89c83a","target":"record","created_at":"2026-07-05T09:27:18Z","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":"ea4811f4b8205df6a52b9b9cda582b268dc3166fc7e996bc6290f2dcb2599bdd","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-05-27T12:16:42Z","title_canon_sha256":"7993f5170d3647ba3f03e028943f4ab0463cdac59610b70091f76a2e63255045"},"schema_version":"1.0","source":{"id":"2105.13086","kind":"arxiv","version":3}},"canonical_sha256":"47a6e3774931ad50ea6023342b823c690fb2ccfb9dbb49fa8fb1732a563713b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47a6e3774931ad50ea6023342b823c690fb2ccfb9dbb49fa8fb1732a563713b0","first_computed_at":"2026-07-05T09:27:18.113766Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:18.113766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sYgiD0vuHnoVO3qB5B6hNpYE4BBf4jJrI3N9gWRX6tRK5aZ98Z6SvyvPIOwnv41wPq5BmE1kF3VRMxGzN6a/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:18.114194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.13086","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ee25bef7352a6994ae1f7e1bddc2ba4769afc62ee3b62d68046688f1e89c83a","sha256:1a00de8519908620ffe4cce97d51af65275546edfe089b502d8ad1433d7ecc1c"],"state_sha256":"29b05e7e0d6f08507f2dbd5aac4bff17699ebff0d353b89e56b5989e99ee8e10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQBBimGQY8CX3dXNy0i9jpqIpYPIh/xeUpZ3iZK3EFKKRXgEH4qZhwhyG5AvTTG30JzWu97ONCW2xxTsphWjCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T17:51:32.707943Z","bundle_sha256":"50b8eed3e8cc72839805692f8f7eefec5a8b8995915c97757c77ea731794d9fa"}}