4th International Conference on Spoken Language Processing

Philadelphia, PA, USA
October 3-6, 1996

Lexical Stress Detection on Stress-minimal Word Pairs

Goangshiuan S. Ying, Leah H. Jamieson, Ruxin Chen, Carl D. Mitchell

School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA

We present a study on the use of lexical stress classification to aid in the recognition of phonetically similar words. In this study, we use a simple pattern recognition approach to determine which syllable is lexically stressed for phonetically similar word pairs (e.g., PERfect, perFECT) extracted from continuously spoken sentences. We use a combination of two features from the acoustic correlates of lexical stress, and assume multivariate Gaussian distributions to form a Bayesian classifier. The features used are normalized energy and duration of the vowel for each syllable of the word. We evaluate several normalization methods. Two sets of sentences were designed for this study. For the pilot experiment, the classification accuracy on words from the natural sentence set was 89.9% and on words from the control sentence set was 100%. To improve the performance, three-feature classifiers, which included two normalized energy features and one normalized duration feature, were developed. The classification accuracy on words from the natural sentence set was 97.23%.

Full Paper

Bibliographic reference.  Ying, Goangshiuan S. / Jamieson, Leah H. / Chen, Ruxin / Mitchell, Carl D. (1996): "Lexical stress detection on stress-minimal word pairs", In ICSLP-1996, 1612-1615.