English

Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis

Computer Vision and Pattern Recognition 2017-09-01 v2

Abstract

We study the problem of acoustic feature learning in the setting where we have access to another (non-acoustic) modality for feature learning but not at test time. We use deep variational canonical correlation analysis (VCCA), a recently proposed deep generative method for multi-view representation learning. We also extend VCCA with improved latent variable priors and with adversarial learning. Compared to other techniques for multi-view feature learning, VCCA's advantages include an intuitive latent variable interpretation and a variational lower bound objective that can be trained end-to-end efficiently. We compare VCCA and its extensions with previous feature learning methods on the University of Wisconsin X-ray Microbeam Database, and show that VCCA-based feature learning improves over previous methods for speaker-independent phonetic recognition.

Keywords

Cite

@article{arxiv.1708.04673,
  title  = {Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis},
  author = {Qingming Tang and Weiran Wang and Karen Livescu},
  journal= {arXiv preprint arXiv:1708.04673},
  year   = {2017}
}
R2 v1 2026-06-22T21:15:33.464Z