Pronunciation scoring for Indian English learners using a phone recognition system
Chitralekha Bhat, K. L. Srinivas, Preeti Rao · 2010
Feedback on pronunciation or articulation is an important component of spoken language teaching. Automating this aspect with speech recognition technology has been an active area of research in the context of computer-aided language-learning systems. Well-known limitations in the accuracy of automatic speech recognition (ASR) systems pose challenges to the reliable detection of pronunciation errors in the speech of non-native speakers. We present the design of a pronunciation scoring system using a phone recognizer developed with the popular HTK and CMU Sphinx HMM-based ASR toolkits. The system is evaluated on Indian English speech in the realistic situation where there is no matching database available for training the speech recognizer. Different approaches to the training of acoustic models and to constraining the phone recognition system are investigated.