Sixth European Conference on Speech Communication and Technology
Previous work has shown that connectionist learning systems can simulate important aspects of the categorization of speech sounds by human and animal listeners. Training is on repre-sentations of synthetic, exemplar voiced and unvoiced stop consonants passed through a computational model of the auditory periphery. In this work, we use the modern inductive inference technique of support vector machines (SVMs) as the learning system. Visualization of the SVMís weight vector reveals what has been learned about the voiced/unvoiced distinction.
Full Paper (PDF) Gnu-Zipped Postscript
Bibliographic reference. Damper, Robert I. / Gunn, Steve R. (1999): "Learning phonetic distinctions from speech signals", In EUROSPEECH'99, 2675-2678.