{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:G3F4BGP23VQGL46P7WFNLJV7WC","short_pith_number":"pith:G3F4BGP2","schema_version":"1.0","canonical_sha256":"36cbc099fadd6065f3cffd8ad5a6bfb08b0d3601eae633422a08c98ecd77c861","source":{"kind":"arxiv","id":"2012.14788","version":2},"attestation_state":"computed","paper":{"title":"Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alicja Serafinowicz, Bozena Kostek, Daniel Korzekwa, Grzegorz Beringer, Jaime Lorenzo-Trueba, Jasha Droppo, Roberto Barra-Chicote, Szymon Zaporowski, Thomas Drugman","submitted_at":"2020-12-29T14:59:49Z","abstract_excerpt":"This paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically derives optimal syllable-level representation from frame-level and phoneme-level audio features. Training this model is challenging because of the limited amount of incorre"},"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":"2012.14788","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-12-29T14:59:49Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"3e6a7408ba82c98a29af3a78a30600dfb218bac6419a298dfc0f0146a23b505b","abstract_canon_sha256":"191552178aed1d4894e5e6e5a2adbd0bbc4b7a570319d6a4ed603fc654b14ec6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:43.564779Z","signature_b64":"k6FM30G+w6lXAZxOK+2HI/tA9LQenw+GmLy7+2swIHgk4G7483aUx2mF1i0DT602zrvLpNEmDV8ff+TC5U1CCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36cbc099fadd6065f3cffd8ad5a6bfb08b0d3601eae633422a08c98ecd77c861","last_reissued_at":"2026-07-05T02:46:43.564354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:43.564354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Alicja Serafinowicz, Bozena Kostek, Daniel Korzekwa, Grzegorz Beringer, Jaime Lorenzo-Trueba, Jasha Droppo, Roberto Barra-Chicote, Szymon Zaporowski, Thomas Drugman","submitted_at":"2020-12-29T14:59:49Z","abstract_excerpt":"This paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically derives optimal syllable-level representation from frame-level and phoneme-level audio features. Training this model is challenging because of the limited amount of incorre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.14788","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/2012.14788/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":"2012.14788","created_at":"2026-07-05T02:46:43.564421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.14788v2","created_at":"2026-07-05T02:46:43.564421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.14788","created_at":"2026-07-05T02:46:43.564421+00:00"},{"alias_kind":"pith_short_12","alias_value":"G3F4BGP23VQG","created_at":"2026-07-05T02:46:43.564421+00:00"},{"alias_kind":"pith_short_16","alias_value":"G3F4BGP23VQGL46P","created_at":"2026-07-05T02:46:43.564421+00:00"},{"alias_kind":"pith_short_8","alias_value":"G3F4BGP2","created_at":"2026-07-05T02:46:43.564421+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27380","citing_title":"A Survey of Automated Presentation Coaching: Systems, Methods, and Open Challenges","ref_index":130,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G3F4BGP23VQGL46P7WFNLJV7WC","json":"https://pith.science/pith/G3F4BGP23VQGL46P7WFNLJV7WC.json","graph_json":"https://pith.science/api/pith-number/G3F4BGP23VQGL46P7WFNLJV7WC/graph.json","events_json":"https://pith.science/api/pith-number/G3F4BGP23VQGL46P7WFNLJV7WC/events.json","paper":"https://pith.science/paper/G3F4BGP2"},"agent_actions":{"view_html":"https://pith.science/pith/G3F4BGP23VQGL46P7WFNLJV7WC","download_json":"https://pith.science/pith/G3F4BGP23VQGL46P7WFNLJV7WC.json","view_paper":"https://pith.science/paper/G3F4BGP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.14788&json=true","fetch_graph":"https://pith.science/api/pith-number/G3F4BGP23VQGL46P7WFNLJV7WC/graph.json","fetch_events":"https://pith.science/api/pith-number/G3F4BGP23VQGL46P7WFNLJV7WC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G3F4BGP23VQGL46P7WFNLJV7WC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G3F4BGP23VQGL46P7WFNLJV7WC/action/storage_attestation","attest_author":"https://pith.science/pith/G3F4BGP23VQGL46P7WFNLJV7WC/action/author_attestation","sign_citation":"https://pith.science/pith/G3F4BGP23VQGL46P7WFNLJV7WC/action/citation_signature","submit_replication":"https://pith.science/pith/G3F4BGP23VQGL46P7WFNLJV7WC/action/replication_record"}},"created_at":"2026-07-05T02:46:43.564421+00:00","updated_at":"2026-07-05T02:46:43.564421+00:00"}