Multi-view Acoustic Feature Learning Using Articulatory Measurements

Abstract

We consider the problem of learning a linear transformation of acoustic feature vectors for phonetic frame classification, in a setting where articulatory measurements are available at training time. We use the acoustic and articulatory data together in a multi-view learning approach, in particular using canonical correlation analysis to learn linear… (More)

Topics

5 Figures and Tables

Cite this paper

@inproceedings{Bharadwaj2012MultiviewAF, title={Multi-view Acoustic Feature Learning Using Articulatory Measurements}, author={Sujeeth Bharadwaj and Raman Arora and Karen Livescu and Mark Hasegawa-Johnson}, year={2012} }