Toward an Understanding of the Role of Speech Recognition in Non-Native Speech Assessment
- Author(s):
- Zechner, Klaus; Bejar, Isaac I.; Hemat, Ramin
- Publication Year:
- 2007
- Report Number:
- RR-07-02, TOEFLiBT-02
- Source:
- Document Type:
- Subject/Key Words:
- Assessment spoken language assessment automatic spoken language assessment
Abstract
The increasing availability and performance of computer-based testing has prompted more research on the automatic assessment of language and speaking proficiency. In this investigation, we evaluated the feasibility of using an off-the-shelf speech-recognition system for scoring speaking prompts from the LanguEdge field test of 2002. We first established the level of agreement between two trained scorers. We then adapted a speech engine to the language backgrounds and proficiency ranges of the speakers and develop a classification and regression tree (CART) for each of five prompts based on features computed from the output of the speech recognizer. In a validation on held-out data, we found that while our features are not sufficiently comprehensive to adequately score these prompts, collectively these features appear to capture reliably some aspects of speaking proficiency.