Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891613731> ?p ?o ?g. }
- W2891613731 endingPage "56" @default.
- W2891613731 startingPage "47" @default.
- W2891613731 abstract "With increasing global demand for learning English as a second language, there has been considerable interest in methods of automatic assessment of spoken language proficiency for use in interactive electronic learning tools as well as for grading candidates for formal qualifications. This paper presents an automatic system to address the assessment of spontaneous spoken language. Prompts or questions requiring spontaneous speech responses elicit more natural speech which better reflects a learner’s proficiency level than read speech. In addition to the challenges of highly variable non-native, learner, speech and noisy real-world recording conditions, this requires any automatic system to handle disfluent, non-grammatical, spontaneous speech with the underlying text unknown. To handle these, a strong deep learning based speech recognition system is applied in combination with a Gaussian Process (GP) grader. A range of features derived from the audio using the recognition hypothesis are investigated for their efficacy in the automatic grader. The proposed system is shown to predict grades at a similar level to the original examiner graders on real candidate entries. Interpolation with the examiner grades further boosts performance. The ability to reject poorly estimated grades is also important and measures are proposed to evaluate the performance of rejection schemes. The GP variance is used to decide which automatic grades should be rejected. Back-off to an expert grader for the least confident grades gives gains." @default.
- W2891613731 created "2018-09-27" @default.
- W2891613731 creator A5024410454 @default.
- W2891613731 creator A5032046290 @default.
- W2891613731 creator A5046799023 @default.
- W2891613731 creator A5050766679 @default.
- W2891613731 creator A5071054399 @default.
- W2891613731 creator A5077892555 @default.
- W2891613731 creator A5080001860 @default.
- W2891613731 date "2018-11-01" @default.
- W2891613731 modified "2023-10-16" @default.
- W2891613731 title "Towards automatic assessment of spontaneous spoken English" @default.
- W2891613731 cites W1032614754 @default.
- W2891613731 cites W1979364015 @default.
- W2891613731 cites W1993882792 @default.
- W2891613731 cites W2002342963 @default.
- W2891613731 cites W2023155336 @default.
- W2891613731 cites W2030026461 @default.
- W2891613731 cites W2048526313 @default.
- W2891613731 cites W2091359957 @default.
- W2891613731 cites W2091856355 @default.
- W2891613731 cites W2097316030 @default.
- W2891613731 cites W2106554350 @default.
- W2891613731 cites W2132481658 @default.
- W2891613731 cites W2139008940 @default.
- W2891613731 cites W2146871184 @default.
- W2891613731 cites W2151381157 @default.
- W2891613731 cites W2160815625 @default.
- W2891613731 cites W2169189000 @default.
- W2891613731 cites W2510063686 @default.
- W2891613731 cites W4205130185 @default.
- W2891613731 cites W4249795127 @default.
- W2891613731 doi "https://doi.org/10.1016/j.specom.2018.09.002" @default.
- W2891613731 hasPublicationYear "2018" @default.
- W2891613731 type Work @default.
- W2891613731 sameAs 2891613731 @default.
- W2891613731 citedByCount "20" @default.
- W2891613731 countsByYear W28916137312018 @default.
- W2891613731 countsByYear W28916137312019 @default.
- W2891613731 countsByYear W28916137312020 @default.
- W2891613731 countsByYear W28916137312021 @default.
- W2891613731 countsByYear W28916137312022 @default.
- W2891613731 countsByYear W28916137312023 @default.
- W2891613731 crossrefType "journal-article" @default.
- W2891613731 hasAuthorship W2891613731A5024410454 @default.
- W2891613731 hasAuthorship W2891613731A5032046290 @default.
- W2891613731 hasAuthorship W2891613731A5046799023 @default.
- W2891613731 hasAuthorship W2891613731A5050766679 @default.
- W2891613731 hasAuthorship W2891613731A5071054399 @default.
- W2891613731 hasAuthorship W2891613731A5077892555 @default.
- W2891613731 hasAuthorship W2891613731A5080001860 @default.
- W2891613731 hasBestOaLocation W28916137312 @default.
- W2891613731 hasConcept C121955636 @default.
- W2891613731 hasConcept C127413603 @default.
- W2891613731 hasConcept C134306372 @default.
- W2891613731 hasConcept C144133560 @default.
- W2891613731 hasConcept C147176958 @default.
- W2891613731 hasConcept C154945302 @default.
- W2891613731 hasConcept C182365436 @default.
- W2891613731 hasConcept C195324797 @default.
- W2891613731 hasConcept C196083921 @default.
- W2891613731 hasConcept C204321447 @default.
- W2891613731 hasConcept C2776230583 @default.
- W2891613731 hasConcept C2777286243 @default.
- W2891613731 hasConcept C28490314 @default.
- W2891613731 hasConcept C33923547 @default.
- W2891613731 hasConcept C41008148 @default.
- W2891613731 hasConceptScore W2891613731C121955636 @default.
- W2891613731 hasConceptScore W2891613731C127413603 @default.
- W2891613731 hasConceptScore W2891613731C134306372 @default.
- W2891613731 hasConceptScore W2891613731C144133560 @default.
- W2891613731 hasConceptScore W2891613731C147176958 @default.
- W2891613731 hasConceptScore W2891613731C154945302 @default.
- W2891613731 hasConceptScore W2891613731C182365436 @default.
- W2891613731 hasConceptScore W2891613731C195324797 @default.
- W2891613731 hasConceptScore W2891613731C196083921 @default.
- W2891613731 hasConceptScore W2891613731C204321447 @default.
- W2891613731 hasConceptScore W2891613731C2776230583 @default.
- W2891613731 hasConceptScore W2891613731C2777286243 @default.
- W2891613731 hasConceptScore W2891613731C28490314 @default.
- W2891613731 hasConceptScore W2891613731C33923547 @default.
- W2891613731 hasConceptScore W2891613731C41008148 @default.
- W2891613731 hasLocation W28916137311 @default.
- W2891613731 hasLocation W28916137312 @default.
- W2891613731 hasOpenAccess W2891613731 @default.
- W2891613731 hasPrimaryLocation W28916137311 @default.
- W2891613731 hasRelatedWork W1552159754 @default.
- W2891613731 hasRelatedWork W1563618553 @default.
- W2891613731 hasRelatedWork W159132833 @default.
- W2891613731 hasRelatedWork W180507639 @default.
- W2891613731 hasRelatedWork W1806995473 @default.
- W2891613731 hasRelatedWork W1986021162 @default.
- W2891613731 hasRelatedWork W2293457016 @default.
- W2891613731 hasRelatedWork W2977842567 @default.
- W2891613731 hasRelatedWork W3107474891 @default.
- W2891613731 hasRelatedWork W1872130062 @default.
- W2891613731 hasVolume "104" @default.
- W2891613731 isParatext "false" @default.