ResearchSpace

Segmentation and accuracy-based scores for the automatic assessment of oral proficiency for proficient L2 speakers

Show simple item record

dc.contributor.author De Wet, Febe
dc.contributor.author Muller, P
dc.contributor.author Van der Walt, C
dc.contributor.author Niesler, T
dc.date.accessioned 2012-02-24T12:32:33Z
dc.date.available 2012-02-24T12:32:33Z
dc.date.issued 2010-11
dc.identifier.citation De Wet, F, Muller, P, Van der Walt, C and Niesler, T. Segmentation and accuracy-based scores for the automatic assessment of oral proficiency for proficient L2 speakers. Twenty-First Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2010), Stellenbosch Institute for Advanced Study (STIAS), Stellenbosch, South Africa, 22-23 November 2010 en_US
dc.identifier.isbn 978-0-7992-2470-2
dc.identifier.uri http://www.dsp.sun.ac.za/~trn/reports/dewet+muller+vanderwalt+niesler_prasa10.pdf
dc.identifier.uri http://www.prasa.org/proceedings/2010/prasa2010-13.pdf
dc.identifier.uri http://hdl.handle.net/10204/5599
dc.description Twenty-First Annual Symposium of the Pattern Recognition Association of South Africa (PRASA 2010), Stellenbosch Institute for Advanced Study (STIAS), Stellenbosch, South Africa, 22-23 November 2010 en_US
dc.description.abstract This paper reports on the automatic assessment of oral proficiency for advanced second language speakers. A spoken dialogue system is used to guide students through an oral test and to record their answers. Indicators of oral proficiency are automatically derived from the recordings and compared with human ratings of the same data. The proficiency indicators investigated here are based on the temporal properties of the students’ speech as well as the their ability to repeat test prompts accurately. Results indicate that, both for segmentation as well as accuracy-based scores, the most simple scores correlate best with the humans’ opinion on the students’ proficiency. Combining different scores using multiple linear regression leads to marginally higher correlations. However, these improvements are too small to justify the associated increase in the computational complexity of the system. en_US
dc.language.iso en en_US
dc.publisher PRASA en_US
dc.relation.ispartofseries Workflow;8026
dc.subject Second language oral proficiency en_US
dc.subject Oral proficiency en_US
dc.subject L2 speakers en_US
dc.title Segmentation and accuracy-based scores for the automatic assessment of oral proficiency for proficient L2 speakers en_US
dc.type Conference Presentation en_US
dc.identifier.apacitation De Wet, F., Muller, P., Van der Walt, C., & Niesler, T. (2010). Segmentation and accuracy-based scores for the automatic assessment of oral proficiency for proficient L2 speakers. PRASA. http://hdl.handle.net/10204/5599 en_ZA
dc.identifier.chicagocitation De Wet, Febe, P Muller, C Van der Walt, and T Niesler. "Segmentation and accuracy-based scores for the automatic assessment of oral proficiency for proficient L2 speakers." (2010): http://hdl.handle.net/10204/5599 en_ZA
dc.identifier.vancouvercitation De Wet F, Muller P, Van der Walt C, Niesler T, Segmentation and accuracy-based scores for the automatic assessment of oral proficiency for proficient L2 speakers; PRASA; 2010. http://hdl.handle.net/10204/5599 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - De Wet, Febe AU - Muller, P AU - Van der Walt, C AU - Niesler, T AB - This paper reports on the automatic assessment of oral proficiency for advanced second language speakers. A spoken dialogue system is used to guide students through an oral test and to record their answers. Indicators of oral proficiency are automatically derived from the recordings and compared with human ratings of the same data. The proficiency indicators investigated here are based on the temporal properties of the students’ speech as well as the their ability to repeat test prompts accurately. Results indicate that, both for segmentation as well as accuracy-based scores, the most simple scores correlate best with the humans’ opinion on the students’ proficiency. Combining different scores using multiple linear regression leads to marginally higher correlations. However, these improvements are too small to justify the associated increase in the computational complexity of the system. DA - 2010-11 DB - ResearchSpace DP - CSIR KW - Second language oral proficiency KW - Oral proficiency KW - L2 speakers LK - https://researchspace.csir.co.za PY - 2010 SM - 978-0-7992-2470-2 T1 - Segmentation and accuracy-based scores for the automatic assessment of oral proficiency for proficient L2 speakers TI - Segmentation and accuracy-based scores for the automatic assessment of oral proficiency for proficient L2 speakers UR - http://hdl.handle.net/10204/5599 ER - en_ZA


Files in this item

This item appears in the following Collection(s)

Show simple item record