ITRW on Experimental Linguistics

Athens, Greece
August 28-30, 2006

Towards Multilingual Articulatory Feature Recognition with Support Vector Machines

Jan Macek, Anja Geumann, Julie Carson-Berndsen

School of Computer Science and Informatics, University College Dublin, Ireland

We present experiments on mono-lingual and cross-lingual articulatory feature recognition for English and German speech data. Our goal is to investigate to what extent it is possible to derive and reuse articulatory feature recognizers, whether particular features are better suited to this task. Finally whether this goal is practically achievable with the chosen machine learning technique and the selected set of speech signal descriptors.

Full Paper

Bibliographic reference.  Macek, Jan / Geumann, Anja / Carson-Berndsen, Julie (2006): "Towards multilingual articulatory feature recognition with support vector machines", In ExLing-2006, 181-184.