Speech Prosody 2010

Chicago, IL, USA
May 10-14, 2010

An Entropy-Based Approach for Comparing Prosodic Properties in Tonal and Pitch Accent Languages

Raymond W. M. Ng (1), Cheung-Chi Leung (2), Tan Lee (1), Bin Ma (2), Haizhou Li (2,3)

(1) Department of Electronic Engineering, the Chinese University of Hong Kong, Hong Kong
(2) Institute for Infocomm Research, Singapore
(3) Department of Computer Science and Statistics, University of Eastern Finland, Finland

Our previous work shows strong prosodic characteristics are present in tonal and pitch accent languages leading to better performance in detecting these languages. This study uses an entropy-based approach to analyze prosodic features for effective modeling. 17 tonal or pitch accent languages, including a number of under-resourced languages in Africa, are studied. Prosodic trigrams are rated as either strong, moderate or weak according to the language-specific information they contain. The three-level rating helps to find the most efficient prosodic trigrams for language recognition. The feature inventory is reduced by 80% while performance degradation is acceptable. Important prosodic attributes found by analysis reflect the linguistic facts in different languages in nice manners. With this analysis method, selection to an expanded prosodic feature inventory can be done to explore better performance in detecting non-tonal languages.

Index Terms: Language recognition, entropy, tonal languages, pitch accent languages, under-resourced languages

Full Paper

Bibliographic reference.  Ng, Raymond W. M. / Leung, Cheung-Chi / Lee, Tan / Ma, Bin / Li, Haizhou (2010): "An entropy-based approach for comparing prosodic properties in tonal and pitch accent languages", In SP-2010, paper 093.