{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:US6ZZVUXNBYT33QGGO4WAAFKOC","short_pith_number":"pith:US6ZZVUX","schema_version":"1.0","canonical_sha256":"a4bd9cd69768713dee0633b96000aa70813715531c09d2fd524cf27aa4e82074","source":{"kind":"arxiv","id":"2211.00923","version":3},"attestation_state":"computed","paper":{"title":"SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ahmed Ali, Hamdy Mubarak, Shammur Absar Chowdhury, Shazia Afzal, Yassine El Kheir","submitted_at":"2022-11-02T07:13:30Z","abstract_excerpt":"The lack of labeled second language (L2) speech data is a major challenge in designing mispronunciation detection models. We introduce SpeechBlender - a fine-grained data augmentation pipeline for generating mispronunciation errors to overcome such data scarcity. The SpeechBlender utilizes varieties of masks to target different regions of phonetic units, and use the mixing factors to linearly interpolate raw speech signals while augmenting pronunciation. The masks facilitate smooth blending of the signals, generating more effective samples than the `Cut/Paste' method. Our proposed technique ac"},"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":"2211.00923","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-11-02T07:13:30Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"3047222f6285d1e79bfe194b228632e7ced9cce50bb70ee4ae7f243a9166168d","abstract_canon_sha256":"624e9a11d3f5172d44ebf5293dda980613d61d83022709b90b38f46af666c287"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:02.663722Z","signature_b64":"etdLzfoD8z+CVXA6HxA7vhcIiR7m36X/zGIieZtJxgTOL4m80Yw4mVyM0nDQQ3LHxf7dmfdVxa7KstkONrVTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4bd9cd69768713dee0633b96000aa70813715531c09d2fd524cf27aa4e82074","last_reissued_at":"2026-07-05T06:30:02.663214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:02.663214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ahmed Ali, Hamdy Mubarak, Shammur Absar Chowdhury, Shazia Afzal, Yassine El Kheir","submitted_at":"2022-11-02T07:13:30Z","abstract_excerpt":"The lack of labeled second language (L2) speech data is a major challenge in designing mispronunciation detection models. We introduce SpeechBlender - a fine-grained data augmentation pipeline for generating mispronunciation errors to overcome such data scarcity. The SpeechBlender utilizes varieties of masks to target different regions of phonetic units, and use the mixing factors to linearly interpolate raw speech signals while augmenting pronunciation. The masks facilitate smooth blending of the signals, generating more effective samples than the `Cut/Paste' method. Our proposed technique ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00923","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/2211.00923/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":"2211.00923","created_at":"2026-07-05T06:30:02.663276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00923v3","created_at":"2026-07-05T06:30:02.663276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00923","created_at":"2026-07-05T06:30:02.663276+00:00"},{"alias_kind":"pith_short_12","alias_value":"US6ZZVUXNBYT","created_at":"2026-07-05T06:30:02.663276+00:00"},{"alias_kind":"pith_short_16","alias_value":"US6ZZVUXNBYT33QG","created_at":"2026-07-05T06:30:02.663276+00:00"},{"alias_kind":"pith_short_8","alias_value":"US6ZZVUX","created_at":"2026-07-05T06:30:02.663276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07722","citing_title":"Towards a Unified Benchmark for Arabic Pronunciation Assessment: Quranic Recitation as Case Study","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/US6ZZVUXNBYT33QGGO4WAAFKOC","json":"https://pith.science/pith/US6ZZVUXNBYT33QGGO4WAAFKOC.json","graph_json":"https://pith.science/api/pith-number/US6ZZVUXNBYT33QGGO4WAAFKOC/graph.json","events_json":"https://pith.science/api/pith-number/US6ZZVUXNBYT33QGGO4WAAFKOC/events.json","paper":"https://pith.science/paper/US6ZZVUX"},"agent_actions":{"view_html":"https://pith.science/pith/US6ZZVUXNBYT33QGGO4WAAFKOC","download_json":"https://pith.science/pith/US6ZZVUXNBYT33QGGO4WAAFKOC.json","view_paper":"https://pith.science/paper/US6ZZVUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00923&json=true","fetch_graph":"https://pith.science/api/pith-number/US6ZZVUXNBYT33QGGO4WAAFKOC/graph.json","fetch_events":"https://pith.science/api/pith-number/US6ZZVUXNBYT33QGGO4WAAFKOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/US6ZZVUXNBYT33QGGO4WAAFKOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/US6ZZVUXNBYT33QGGO4WAAFKOC/action/storage_attestation","attest_author":"https://pith.science/pith/US6ZZVUXNBYT33QGGO4WAAFKOC/action/author_attestation","sign_citation":"https://pith.science/pith/US6ZZVUXNBYT33QGGO4WAAFKOC/action/citation_signature","submit_replication":"https://pith.science/pith/US6ZZVUXNBYT33QGGO4WAAFKOC/action/replication_record"}},"created_at":"2026-07-05T06:30:02.663276+00:00","updated_at":"2026-07-05T06:30:02.663276+00:00"}