Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385570535> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4385570535 abstract "A common metric for evaluating Automatic Speech Recognition (ASR) is Word Error Rate (WER) which solely takes into account discrepancies at the word-level. Although useful, WER is not guaranteed to correlate well with human judgment or performance on downstream tasks that use ASR. Meaningful assessment of ASR mistakes becomes even more important in high-stake scenarios such as health-care. We propose 2 general measures to evaluate the severity of mistakes made by ASR systems, one based on sentiment analysis and another based on text embeddings. We evaluate these measures on simulated patient-doctor conversations using 5 ASR systems. Results show that these measures capture characteristics of ASR errors that WER does not. Furthermore, we train an ASR system incorporating severity and demonstrate the potential for using severity not only in the evaluation, but in the development of ASR. Advantages and limitations of this methodology are analyzed and discussed." @default.
- W4385570535 created "2023-08-05" @default.
- W4385570535 creator A5041266343 @default.
- W4385570535 creator A5091012924 @default.
- W4385570535 date "2023-01-01" @default.
- W4385570535 modified "2023-09-27" @default.
- W4385570535 title "Evaluating and Improving Automatic Speech Recognition using Severity" @default.
- W4385570535 doi "https://doi.org/10.18653/v1/2023.bionlp-1.6" @default.
- W4385570535 hasPublicationYear "2023" @default.
- W4385570535 type Work @default.
- W4385570535 citedByCount "0" @default.
- W4385570535 crossrefType "proceedings-article" @default.
- W4385570535 hasAuthorship W4385570535A5041266343 @default.
- W4385570535 hasAuthorship W4385570535A5091012924 @default.
- W4385570535 hasBestOaLocation W43855705351 @default.
- W4385570535 hasConcept C127413603 @default.
- W4385570535 hasConcept C138885662 @default.
- W4385570535 hasConcept C154945302 @default.
- W4385570535 hasConcept C176217482 @default.
- W4385570535 hasConcept C204321447 @default.
- W4385570535 hasConcept C21547014 @default.
- W4385570535 hasConcept C28490314 @default.
- W4385570535 hasConcept C40969351 @default.
- W4385570535 hasConcept C41008148 @default.
- W4385570535 hasConcept C41895202 @default.
- W4385570535 hasConcept C90805587 @default.
- W4385570535 hasConceptScore W4385570535C127413603 @default.
- W4385570535 hasConceptScore W4385570535C138885662 @default.
- W4385570535 hasConceptScore W4385570535C154945302 @default.
- W4385570535 hasConceptScore W4385570535C176217482 @default.
- W4385570535 hasConceptScore W4385570535C204321447 @default.
- W4385570535 hasConceptScore W4385570535C21547014 @default.
- W4385570535 hasConceptScore W4385570535C28490314 @default.
- W4385570535 hasConceptScore W4385570535C40969351 @default.
- W4385570535 hasConceptScore W4385570535C41008148 @default.
- W4385570535 hasConceptScore W4385570535C41895202 @default.
- W4385570535 hasConceptScore W4385570535C90805587 @default.
- W4385570535 hasLocation W43855705351 @default.
- W4385570535 hasOpenAccess W4385570535 @default.
- W4385570535 hasPrimaryLocation W43855705351 @default.
- W4385570535 hasRelatedWork W1937192591 @default.
- W4385570535 hasRelatedWork W2019914509 @default.
- W4385570535 hasRelatedWork W2048917925 @default.
- W4385570535 hasRelatedWork W2134995938 @default.
- W4385570535 hasRelatedWork W2138093906 @default.
- W4385570535 hasRelatedWork W2251677926 @default.
- W4385570535 hasRelatedWork W3038160611 @default.
- W4385570535 hasRelatedWork W3101868899 @default.
- W4385570535 hasRelatedWork W3150750326 @default.
- W4385570535 hasRelatedWork W2116192687 @default.
- W4385570535 isParatext "false" @default.
- W4385570535 isRetracted "false" @default.
- W4385570535 workType "article" @default.