12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Using a Genetic Algorithm to Estimate Parameters of a Coarticulation Model

Brian O. Bush, John-Paul Hosom, Alexander Kain, Akiko Amano-Kusumoto

Oregon Health & Science University, USA

We present a real-coded genetic algorithm that efficiently estimates parameters of a formant trajectory model. The genetic algorithm uses roulette-wheel selection and elitism to minimize the root mean square error between the observed formant trajectory and the model trajectory. Parameters, including vowel and consonant target values and coarticulation parameters, are estimated for a corpus of English clear and conversational CVC words. Results show consistent consonant formant targets, even when those consonants do not themselves have formant structure. We also present findings of a relationship between a coarticulation parameter and the consonant identity.

Full Paper

Bibliographic reference.  Bush, Brian O. / Hosom, John-Paul / Kain, Alexander / Amano-Kusumoto, Akiko (2011): "Using a genetic algorithm to estimate parameters of a coarticulation model", In INTERSPEECH-2011, 2677-2680.