ISCA International Workshop on Speech and Language Technology in Education (SLaTE 2011)

Venice, Italy
August 24-26, 2011

A method for predicting stressed words in English Jazz Chants

Ryo Nagata (1), Toshiaki Marueki (1), Kotaro Funakoshi (2), Tatsuya Kitamura (1), Mikio Nakano (2)

(1) Konan University, Japan; (2) Honda Research Institute Japan Co., Ltd., Japan

To acquire a second language, one must develop an ear and tongue for the correct stress and intonation patterns of that language. In English language teaching, there is an effective method called Jazz Chants for working on the sound system. In this paper, we propose a method for predicting stressed words, which play a crucial role in Jazz Chants. The proposed method is specially designed for stress prediction in Jazz chants. It exploits several sources of information including words, POSs, sentence types, and the constraint on the number of stressed words in a chant text. Experiments show that the proposed method achieves an &# 4;-measure of 0.936 and outperforms the other methods implemented for comparison. The proposed method is expected to be useful in supporting non-native teachers of English when they teach chants to students and create chant texts with stress marks from arbitrary texts.
Index Terms. language learning, stress prediction, teaching material generation, Jazz Chants, stress-timed rhythm

Full Paper

Bibliographic reference.  Nagata, Ryo / Marueki, Toshiaki / Funakoshi, Kotaro / Kitamura, Tatsuya / Nakano, Mikio (2011): "A method for predicting stressed words in English jazz chants", In SLaTE-2011, 81-84.