{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NM7REPF2AZBBNIZH3KT6PJTEVK","short_pith_number":"pith:NM7REPF2","schema_version":"1.0","canonical_sha256":"6b3f123cba064216a327daa7e7a664aaadff1823bffb33c18aae2e6e348aba55","source":{"kind":"arxiv","id":"2207.01718","version":1},"attestation_state":"computed","paper":{"title":"BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Brooke Stephenson, Laurent Besacier, Laurent Girin, Thomas Hueber","submitted_at":"2022-07-04T20:43:41Z","abstract_excerpt":"Several recent studies have tested the use of transformer language model representations to infer prosodic features for text-to-speech synthesis (TTS). While these studies have explored prosody in general, in this work, we look specifically at the prediction of contrastive focus on personal pronouns. This is a particularly challenging task as it often requires semantic, discursive and/or pragmatic knowledge to predict correctly. We collect a corpus of utterances containing contrastive focus and we evaluate the accuracy of a BERT model, finetuned to predict quantized acoustic prominence feature"},"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":"2207.01718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-04T20:43:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"5385d8a68ec961163de6743b0b238ada132234fd2bf411a5d8aeebe6a37eae80","abstract_canon_sha256":"0a4ed7944370ae85ca545734341bc54f1f7bf927f77ab96ce71ee44764d93b54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:37:43.432216Z","signature_b64":"aq0GLLsYUIs7tN1sCCEhC5sFD9TAi3M1Rq9ZjYGq7iy3QZ7ax3a0XI9ORUvFfEB3AmqGIqnMQVvIDpvos3iiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b3f123cba064216a327daa7e7a664aaadff1823bffb33c18aae2e6e348aba55","last_reissued_at":"2026-07-05T04:37:43.431872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:37:43.431872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Brooke Stephenson, Laurent Besacier, Laurent Girin, Thomas Hueber","submitted_at":"2022-07-04T20:43:41Z","abstract_excerpt":"Several recent studies have tested the use of transformer language model representations to infer prosodic features for text-to-speech synthesis (TTS). While these studies have explored prosody in general, in this work, we look specifically at the prediction of contrastive focus on personal pronouns. This is a particularly challenging task as it often requires semantic, discursive and/or pragmatic knowledge to predict correctly. We collect a corpus of utterances containing contrastive focus and we evaluate the accuracy of a BERT model, finetuned to predict quantized acoustic prominence feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01718","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/2207.01718/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":"2207.01718","created_at":"2026-07-05T04:37:43.431938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01718v1","created_at":"2026-07-05T04:37:43.431938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01718","created_at":"2026-07-05T04:37:43.431938+00:00"},{"alias_kind":"pith_short_12","alias_value":"NM7REPF2AZBB","created_at":"2026-07-05T04:37:43.431938+00:00"},{"alias_kind":"pith_short_16","alias_value":"NM7REPF2AZBBNIZH","created_at":"2026-07-05T04:37:43.431938+00:00"},{"alias_kind":"pith_short_8","alias_value":"NM7REPF2","created_at":"2026-07-05T04:37:43.431938+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.17494","citing_title":"Improving French Synthetic Speech Quality via SSML Prosody Control","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NM7REPF2AZBBNIZH3KT6PJTEVK","json":"https://pith.science/pith/NM7REPF2AZBBNIZH3KT6PJTEVK.json","graph_json":"https://pith.science/api/pith-number/NM7REPF2AZBBNIZH3KT6PJTEVK/graph.json","events_json":"https://pith.science/api/pith-number/NM7REPF2AZBBNIZH3KT6PJTEVK/events.json","paper":"https://pith.science/paper/NM7REPF2"},"agent_actions":{"view_html":"https://pith.science/pith/NM7REPF2AZBBNIZH3KT6PJTEVK","download_json":"https://pith.science/pith/NM7REPF2AZBBNIZH3KT6PJTEVK.json","view_paper":"https://pith.science/paper/NM7REPF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01718&json=true","fetch_graph":"https://pith.science/api/pith-number/NM7REPF2AZBBNIZH3KT6PJTEVK/graph.json","fetch_events":"https://pith.science/api/pith-number/NM7REPF2AZBBNIZH3KT6PJTEVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NM7REPF2AZBBNIZH3KT6PJTEVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NM7REPF2AZBBNIZH3KT6PJTEVK/action/storage_attestation","attest_author":"https://pith.science/pith/NM7REPF2AZBBNIZH3KT6PJTEVK/action/author_attestation","sign_citation":"https://pith.science/pith/NM7REPF2AZBBNIZH3KT6PJTEVK/action/citation_signature","submit_replication":"https://pith.science/pith/NM7REPF2AZBBNIZH3KT6PJTEVK/action/replication_record"}},"created_at":"2026-07-05T04:37:43.431938+00:00","updated_at":"2026-07-05T04:37:43.431938+00:00"}