Automatic evaluation of quantity contrast in non-native Norwegian speech

Computer assisted language learning (CAPT) has been shown to be effective for learning non-natives pronunciation details of a new language. No automatic pronunciation evaluation system exists for non-native Norwegian. We present initial experiments on the Norwegian quantity contrast between short and long vowels. A database of native and non-native speakers was recorded for training and test respectively. We have used a set of acoustic-phonetic features and combined them in a classifier based on linear discriminant analysis (LDA). The resulting classification rate was 92.3% compared with a human rating. As expected, vowel duration was the most important feature, whereas vowel spectral content contributed insignificantly. The achieved classification rate is promising with respect to making a useful Norwegian CAPT for quantity.