{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:742DXLOHLQ7LO32TUATKU4MZJS","short_pith_number":"pith:742DXLOH","schema_version":"1.0","canonical_sha256":"ff343badc75c3eb76f53a026aa71994cae6d318cb09e1a814e412e3cfad7f47f","source":{"kind":"arxiv","id":"2209.10591","version":1},"attestation_state":"computed","paper":{"title":"Assessing ASR Model Quality on Disordered Speech using BERTScore","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Jimmy Tobin, Katie Seaver, Katrin Tomanek, Qisheng Li, Richard Cave, Subhashini Venugopalan","submitted_at":"2022-09-21T18:33:33Z","abstract_excerpt":"Word Error Rate (WER) is the primary metric used to assess automatic speech recognition (ASR) model quality. It has been shown that ASR models tend to have much higher WER on speakers with speech impairments than typical English speakers. It is hard to determine if models can be be useful at such high error rates. This study investigates the use of BERTScore, an evaluation metric for text generation, to provide a more informative measure of ASR model quality and usefulness. Both BERTScore and WER were compared to prediction errors manually annotated by Speech Language Pathologists for error ty"},"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":"2209.10591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-21T18:33:33Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"61e99af81b4b230c56f03fccb9c6c26b221cc75e66ab2ea7663191c34594328e","abstract_canon_sha256":"8af530a949fbf4464052383d297d438d88a20ecd0b7cd0c97afbd09aa4ccc491"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:04.276050Z","signature_b64":"RoSQ2uaPJ5kiEu5kjbH5lpzNLlbX7Fki5qDxzNzyOF1fd9H3ru+MBBy9ZCDRVGglq9knurPO1gzCyS7m+TcTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff343badc75c3eb76f53a026aa71994cae6d318cb09e1a814e412e3cfad7f47f","last_reissued_at":"2026-07-05T05:00:04.275633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:04.275633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing ASR Model Quality on Disordered Speech using BERTScore","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"eess.AS","authors_text":"Jimmy Tobin, Katie Seaver, Katrin Tomanek, Qisheng Li, Richard Cave, Subhashini Venugopalan","submitted_at":"2022-09-21T18:33:33Z","abstract_excerpt":"Word Error Rate (WER) is the primary metric used to assess automatic speech recognition (ASR) model quality. It has been shown that ASR models tend to have much higher WER on speakers with speech impairments than typical English speakers. It is hard to determine if models can be be useful at such high error rates. This study investigates the use of BERTScore, an evaluation metric for text generation, to provide a more informative measure of ASR model quality and usefulness. Both BERTScore and WER were compared to prediction errors manually annotated by Speech Language Pathologists for error ty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10591","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/2209.10591/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":"2209.10591","created_at":"2026-07-05T05:00:04.275691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10591v1","created_at":"2026-07-05T05:00:04.275691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10591","created_at":"2026-07-05T05:00:04.275691+00:00"},{"alias_kind":"pith_short_12","alias_value":"742DXLOHLQ7L","created_at":"2026-07-05T05:00:04.275691+00:00"},{"alias_kind":"pith_short_16","alias_value":"742DXLOHLQ7LO32T","created_at":"2026-07-05T05:00:04.275691+00:00"},{"alias_kind":"pith_short_8","alias_value":"742DXLOH","created_at":"2026-07-05T05:00:04.275691+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/742DXLOHLQ7LO32TUATKU4MZJS","json":"https://pith.science/pith/742DXLOHLQ7LO32TUATKU4MZJS.json","graph_json":"https://pith.science/api/pith-number/742DXLOHLQ7LO32TUATKU4MZJS/graph.json","events_json":"https://pith.science/api/pith-number/742DXLOHLQ7LO32TUATKU4MZJS/events.json","paper":"https://pith.science/paper/742DXLOH"},"agent_actions":{"view_html":"https://pith.science/pith/742DXLOHLQ7LO32TUATKU4MZJS","download_json":"https://pith.science/pith/742DXLOHLQ7LO32TUATKU4MZJS.json","view_paper":"https://pith.science/paper/742DXLOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10591&json=true","fetch_graph":"https://pith.science/api/pith-number/742DXLOHLQ7LO32TUATKU4MZJS/graph.json","fetch_events":"https://pith.science/api/pith-number/742DXLOHLQ7LO32TUATKU4MZJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/742DXLOHLQ7LO32TUATKU4MZJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/742DXLOHLQ7LO32TUATKU4MZJS/action/storage_attestation","attest_author":"https://pith.science/pith/742DXLOHLQ7LO32TUATKU4MZJS/action/author_attestation","sign_citation":"https://pith.science/pith/742DXLOHLQ7LO32TUATKU4MZJS/action/citation_signature","submit_replication":"https://pith.science/pith/742DXLOHLQ7LO32TUATKU4MZJS/action/replication_record"}},"created_at":"2026-07-05T05:00:04.275691+00:00","updated_at":"2026-07-05T05:00:04.275691+00:00"}