INTERSPEECH 2012
13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Improvement in Automatic Pronunciation Scoring using Additional Basic Scores and Learning to Rank

Liang-Yu Chen (1), Jyh-Shing Roger Jang (2)

(1) Institute of Information Systems and Applications; (2) Department of Computer Science;
National Tsing Hua University, Taiwan

This paper proposes the adoption of different word-level scores in the framework of automatic pronunciation scoring using learning to rank. Six types of phone-level scores are first computed and converted to word-level scores by using average-based, vowel-based, and consonantbased methods. Different score combination methods are then used to combine these word-level scores to obtain the final combined score for the utterance under inspection. The experimental result shows that the learning to rank methods perform better than most of the existing methods, while using all types of word-level scores can lead to some improvement over the original average-based scores.

Index Terms: automatic pronunciation scoring, computer-assisted pronunciation training, learning to rank

Full Paper

Bibliographic reference.  Chen, Liang-Yu / Jang, Jyh-Shing Roger (2012): "Improvement in automatic pronunciation scoring using additional basic scores and learning to rank", In INTERSPEECH-2012, 1295-1298.