ISCA International Workshop on Speech and Language Technology in Education (SLaTE 2009)

Wroxall Abbey Estate, Warwickshire, England
September 3-5, 2009

Automatic Evaluation of Quantity Contrast in Non-Native Norwegian Speech

Ingunn Amdal, Magne H. Johnsen, Eivind Versvik

Department of Electronics and Telecommunications, University of Science and Technology, Trondheim, Norway

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.

Full Paper

Bibliographic reference.  Amdal, Ingunn / Johnsen, Magne H. / Versvik, Eivind (2009): "Automatic evaluation of quantity contrast in non-native Norwegian speech", In SLaTE-2009, 21-24.