Assessment of dutch pronunciation by means of automatic speech recognition technology

Experiments were carried out to determine whether log-likelihood ratios (LRs) can be employed to improve automatic assessment of Dutch pronunciation. Read speech of natives and non-natives was judged by three groups of expert raters and was then analyzed by means of a continuous speech recognizer. Three automatic measures were calculated, two LRs and rate of speech (ros), and then compared with the expert ratings. It appears that expert ratings of pronunciation quality can accurately be predicted on the basis of ros alone and that LRs do not contribute to better prediction. However, LRs can be useful to automatic pronunciation assessment because they can help detect fast speakers who produce totally wrong sentences.