{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MM7WCXIIPVTDUDTKQL7FXFAN7B","short_pith_number":"pith:MM7WCXII","schema_version":"1.0","canonical_sha256":"633f615d087d663a0e6a82fe5b940df84fd701e43f89c36f52f9e6df2ca79e18","source":{"kind":"arxiv","id":"2003.06686","version":1},"attestation_state":"computed","paper":{"title":"Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0","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":"Catherine Lai, Simon King, Zack Hodari","submitted_at":"2020-03-14T19:17:42Z","abstract_excerpt":"In English, prosody adds a broad range of information to segment sequences, from information structure (e.g. contrast) to stylistic variation (e.g. expression of emotion). However, when learning to control prosody in text-to-speech voices, it is not clear what exactly the control is modifying. Existing research on discrete representation learning for prosody has demonstrated high naturalness, but no analysis has been performed on what these representations capture, or if they can generate meaningfully-distinct variants of an utterance. We present a phrase-level variational autoencoder with a m"},"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":"2003.06686","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-03-14T19:17:42Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","stat.ML"],"title_canon_sha256":"627668fc3a43d0d8636701780359140c6cc09b27e0f595a46dde97343d4560c3","abstract_canon_sha256":"9e9719bf4f5feee0880fb43e8aea4824a2c1f33c9a32a9e903431ec6a6cebdae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:26.120373Z","signature_b64":"fANK8gTVBC21hiTRI2TgoGJDp0b06icBkHs27zMD56+REZGn319yjWpS+bCJXdFoBH8rPfdNbKgeH2+aTsYKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"633f615d087d663a0e6a82fe5b940df84fd701e43f89c36f52f9e6df2ca79e18","last_reissued_at":"2026-07-05T01:48:26.119907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:26.119907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0","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":"Catherine Lai, Simon King, Zack Hodari","submitted_at":"2020-03-14T19:17:42Z","abstract_excerpt":"In English, prosody adds a broad range of information to segment sequences, from information structure (e.g. contrast) to stylistic variation (e.g. expression of emotion). However, when learning to control prosody in text-to-speech voices, it is not clear what exactly the control is modifying. Existing research on discrete representation learning for prosody has demonstrated high naturalness, but no analysis has been performed on what these representations capture, or if they can generate meaningfully-distinct variants of an utterance. We present a phrase-level variational autoencoder with a m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.06686","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/2003.06686/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":"2003.06686","created_at":"2026-07-05T01:48:26.119962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.06686v1","created_at":"2026-07-05T01:48:26.119962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.06686","created_at":"2026-07-05T01:48:26.119962+00:00"},{"alias_kind":"pith_short_12","alias_value":"MM7WCXIIPVTD","created_at":"2026-07-05T01:48:26.119962+00:00"},{"alias_kind":"pith_short_16","alias_value":"MM7WCXIIPVTDUDTK","created_at":"2026-07-05T01:48:26.119962+00:00"},{"alias_kind":"pith_short_8","alias_value":"MM7WCXII","created_at":"2026-07-05T01:48:26.119962+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/MM7WCXIIPVTDUDTKQL7FXFAN7B","json":"https://pith.science/pith/MM7WCXIIPVTDUDTKQL7FXFAN7B.json","graph_json":"https://pith.science/api/pith-number/MM7WCXIIPVTDUDTKQL7FXFAN7B/graph.json","events_json":"https://pith.science/api/pith-number/MM7WCXIIPVTDUDTKQL7FXFAN7B/events.json","paper":"https://pith.science/paper/MM7WCXII"},"agent_actions":{"view_html":"https://pith.science/pith/MM7WCXIIPVTDUDTKQL7FXFAN7B","download_json":"https://pith.science/pith/MM7WCXIIPVTDUDTKQL7FXFAN7B.json","view_paper":"https://pith.science/paper/MM7WCXII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.06686&json=true","fetch_graph":"https://pith.science/api/pith-number/MM7WCXIIPVTDUDTKQL7FXFAN7B/graph.json","fetch_events":"https://pith.science/api/pith-number/MM7WCXIIPVTDUDTKQL7FXFAN7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MM7WCXIIPVTDUDTKQL7FXFAN7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MM7WCXIIPVTDUDTKQL7FXFAN7B/action/storage_attestation","attest_author":"https://pith.science/pith/MM7WCXIIPVTDUDTKQL7FXFAN7B/action/author_attestation","sign_citation":"https://pith.science/pith/MM7WCXIIPVTDUDTKQL7FXFAN7B/action/citation_signature","submit_replication":"https://pith.science/pith/MM7WCXIIPVTDUDTKQL7FXFAN7B/action/replication_record"}},"created_at":"2026-07-05T01:48:26.119962+00:00","updated_at":"2026-07-05T01:48:26.119962+00:00"}