{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5CEZC27ZKFOPVCVXKU64VCAP3F","short_pith_number":"pith:5CEZC27Z","schema_version":"1.0","canonical_sha256":"e889916bf9515cfa8ab7553dca880fd96eaa7a133c48891c081a4db7afd92f20","source":{"kind":"arxiv","id":"1906.04233","version":2},"attestation_state":"computed","paper":{"title":"Using generative modelling to produce varied intonation for speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Oliver Watts, Simon King, Zack Hodari","submitted_at":"2019-06-10T19:05:03Z","abstract_excerpt":"Unlike human speakers, typical text-to-speech (TTS) systems are unable to produce multiple distinct renditions of a given sentence. This has previously been addressed by adding explicit external control. In contrast, generative models are able to capture a distribution over multiple renditions and thus produce varied renditions using sampling. Typical neural TTS models learn the average of the data because they minimise mean squared error. In the context of prosody, taking the average produces flatter, more boring speech: an \"average prosody\". A generative model that can synthesise multiple pr"},"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":"1906.04233","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2019-06-10T19:05:03Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"262d696b617ddb754346b3197c4c459217d96528e5b14dc77fdae89f55eb11fd","abstract_canon_sha256":"75e41220cbf3e176442ef5685d4cd5bde8a16831c2e714b828ae009ee05f4c45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:24.800621Z","signature_b64":"3YQuXTkL3sDHd72O0NfudToA2Yeh3uFCsAvF1V1Ko3YP+th6TAjGWnpIM/X+rSEu3Bo2DBSa88pgALocfMW2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e889916bf9515cfa8ab7553dca880fd96eaa7a133c48891c081a4db7afd92f20","last_reissued_at":"2026-07-05T01:48:24.800256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:24.800256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using generative modelling to produce varied intonation for speech synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","stat.ML"],"primary_cat":"eess.AS","authors_text":"Oliver Watts, Simon King, Zack Hodari","submitted_at":"2019-06-10T19:05:03Z","abstract_excerpt":"Unlike human speakers, typical text-to-speech (TTS) systems are unable to produce multiple distinct renditions of a given sentence. This has previously been addressed by adding explicit external control. In contrast, generative models are able to capture a distribution over multiple renditions and thus produce varied renditions using sampling. Typical neural TTS models learn the average of the data because they minimise mean squared error. In the context of prosody, taking the average produces flatter, more boring speech: an \"average prosody\". A generative model that can synthesise multiple pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04233","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/1906.04233/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":"1906.04233","created_at":"2026-07-05T01:48:24.800326+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04233v2","created_at":"2026-07-05T01:48:24.800326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04233","created_at":"2026-07-05T01:48:24.800326+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CEZC27ZKFOP","created_at":"2026-07-05T01:48:24.800326+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CEZC27ZKFOPVCVX","created_at":"2026-07-05T01:48:24.800326+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CEZC27Z","created_at":"2026-07-05T01:48:24.800326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5CEZC27ZKFOPVCVXKU64VCAP3F","json":"https://pith.science/pith/5CEZC27ZKFOPVCVXKU64VCAP3F.json","graph_json":"https://pith.science/api/pith-number/5CEZC27ZKFOPVCVXKU64VCAP3F/graph.json","events_json":"https://pith.science/api/pith-number/5CEZC27ZKFOPVCVXKU64VCAP3F/events.json","paper":"https://pith.science/paper/5CEZC27Z"},"agent_actions":{"view_html":"https://pith.science/pith/5CEZC27ZKFOPVCVXKU64VCAP3F","download_json":"https://pith.science/pith/5CEZC27ZKFOPVCVXKU64VCAP3F.json","view_paper":"https://pith.science/paper/5CEZC27Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04233&json=true","fetch_graph":"https://pith.science/api/pith-number/5CEZC27ZKFOPVCVXKU64VCAP3F/graph.json","fetch_events":"https://pith.science/api/pith-number/5CEZC27ZKFOPVCVXKU64VCAP3F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CEZC27ZKFOPVCVXKU64VCAP3F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CEZC27ZKFOPVCVXKU64VCAP3F/action/storage_attestation","attest_author":"https://pith.science/pith/5CEZC27ZKFOPVCVXKU64VCAP3F/action/author_attestation","sign_citation":"https://pith.science/pith/5CEZC27ZKFOPVCVXKU64VCAP3F/action/citation_signature","submit_replication":"https://pith.science/pith/5CEZC27ZKFOPVCVXKU64VCAP3F/action/replication_record"}},"created_at":"2026-07-05T01:48:24.800326+00:00","updated_at":"2026-07-05T01:48:24.800326+00:00"}