{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LQ6OQ7EXOQYAOQXLAUCRPZ4VTH","short_pith_number":"pith:LQ6OQ7EX","schema_version":"1.0","canonical_sha256":"5c3ce87c9774300742eb050517e79599de7bbb2f40a420b492b19a049aedab0e","source":{"kind":"arxiv","id":"2604.06191","version":2},"attestation_state":"computed","paper":{"title":"Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists.","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdulrhman Aljouie, Asif Azad, Ayah Othman Sindi, Bdour Alwuqaysi, Ehsan Hoque, MD Sadik Hossain Shanto, Mohammad Sadat Hossain, Sabri Boughorbel, Yahya Bokhari","submitted_at":"2026-03-11T04:10:35Z","abstract_excerpt":"Automated phoneme-level pronunciation assessment is vital for scalable speech therapy and language learning, yet validated tools for Arabic remain scarce. We present Harf-Speech, a modular system scoring Arabic pronunciation at the phoneme level on a clinical scale. It combines an MSA phonetizer, a fine-tuned speech-to-phoneme model, Levenshtein alignment, and a blended scorer using longest common subsequence and edit-distance metrics. We fine-tune three ASR architectures on Arabic phoneme data and benchmark them with zero-shot multimodal models; the best, OmniASR-CTC-1B-v2, achieves 8.92% pho"},"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":true},"canonical_record":{"source":{"id":"2604.06191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-03-11T04:10:35Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"7da72b745669f941c53f604c963e5f999c8fab871f1dab17223f411087c0e19e","abstract_canon_sha256":"a85077a7c51d43c1937f223da245ec11944ec938a12518197b1b027bcb8af9c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:04.509899Z","signature_b64":"cC3Mum4NFv2WkZxGgEv5K1oOWaYNVhqcxmE+rLLkOetEEytDXr1auh1eBXBMqdYKyyYWNQ0NYq1+XTIi+Hz4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c3ce87c9774300742eb050517e79599de7bbb2f40a420b492b19a049aedab0e","last_reissued_at":"2026-06-23T01:12:04.509307Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:04.509307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists.","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdulrhman Aljouie, Asif Azad, Ayah Othman Sindi, Bdour Alwuqaysi, Ehsan Hoque, MD Sadik Hossain Shanto, Mohammad Sadat Hossain, Sabri Boughorbel, Yahya Bokhari","submitted_at":"2026-03-11T04:10:35Z","abstract_excerpt":"Automated phoneme-level pronunciation assessment is vital for scalable speech therapy and language learning, yet validated tools for Arabic remain scarce. We present Harf-Speech, a modular system scoring Arabic pronunciation at the phoneme level on a clinical scale. It combines an MSA phonetizer, a fine-tuned speech-to-phoneme model, Levenshtein alignment, and a blended scorer using longest common subsequence and edit-distance metrics. We fine-tune three ASR architectures on Arabic phoneme data and benchmark them with zero-shot multimodal models; the best, OmniASR-CTC-1B-v2, achieves 8.92% pho"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Harf-Speech attains a Pearson correlation of 0.791 and ICC(2,1) of 0.659 with mean expert scores, outperforming existing end-to-end assessment frameworks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 40 utterances scored by three pathologists are representative of the clinical population and that the blended LCS-plus-edit-distance metric faithfully captures the clinical judgment used by experts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Harf-Speech delivers phoneme-level Arabic pronunciation scores that correlate 0.79 with certified speech-language pathologists on 40 utterances.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"49c329ded3649b5fee6b73e115b2646794f663a6b46d5e5bef41489b010ec591"},"source":{"id":"2604.06191","kind":"arxiv","version":2},"verdict":{"id":"57a87f6b-1df2-4115-a99a-a41f29e8692d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T13:37:38.480667Z","strongest_claim":"Harf-Speech attains a Pearson correlation of 0.791 and ICC(2,1) of 0.659 with mean expert scores, outperforming existing end-to-end assessment frameworks.","one_line_summary":"Harf-Speech delivers phoneme-level Arabic pronunciation scores that correlate 0.79 with certified speech-language pathologists on 40 utterances.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 40 utterances scored by three pathologists are representative of the clinical population and that the blended LCS-plus-edit-distance metric faithfully captures the clinical judgment used by experts.","pith_extraction_headline":"Harf-Speech scores Arabic pronunciation at the phoneme level with 0.791 correlation to expert pathologists."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.06191/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":2,"snapshot_sha256":"6af27d2f2e76041dab127244f663de9259ffb1c0df052de5b323f80f26e4802d"},"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":"2604.06191","created_at":"2026-06-23T01:12:04.509400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.06191v2","created_at":"2026-06-23T01:12:04.509400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.06191","created_at":"2026-06-23T01:12:04.509400+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQ6OQ7EXOQYA","created_at":"2026-06-23T01:12:04.509400+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQ6OQ7EXOQYAOQXL","created_at":"2026-06-23T01:12:04.509400+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQ6OQ7EX","created_at":"2026-06-23T01:12:04.509400+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.06191","citing_title":"Harf-Speech: A Clinically Aligned Framework for Arabic Phoneme-Level Speech Assessment","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH","json":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH.json","graph_json":"https://pith.science/api/pith-number/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/graph.json","events_json":"https://pith.science/api/pith-number/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/events.json","paper":"https://pith.science/paper/LQ6OQ7EX"},"agent_actions":{"view_html":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH","download_json":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH.json","view_paper":"https://pith.science/paper/LQ6OQ7EX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.06191&json=true","fetch_graph":"https://pith.science/api/pith-number/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/graph.json","fetch_events":"https://pith.science/api/pith-number/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/action/storage_attestation","attest_author":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/action/author_attestation","sign_citation":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/action/citation_signature","submit_replication":"https://pith.science/pith/LQ6OQ7EXOQYAOQXLAUCRPZ4VTH/action/replication_record"}},"created_at":"2026-06-23T01:12:04.509400+00:00","updated_at":"2026-06-23T01:12:04.509400+00:00"}