Unsupervised learning of acoustic features via deep canonical correlation analysis
Authors:
- 1 April 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 4590-4594
Abstract
It has been previously shown that, when both acoustic and articulatory training data are available, it is possible to improve phonetic recognition accuracy by learning acoustic features from this multi-view data with canonical correlation analysis (CCA). In contrast with previous work based on linear or kernel CCA, we use the recently proposed deep CCA, where the functional form of the feature mapping is a deep neural network. We apply the approach on a speaker-independent phonetic recognition task using data from the University of Wisconsin X-ray Microbeam Database. Using a tandem-style recognizer on this task, deep CCA features improve over earlier multi-view approaches as well as over articulatory inversion and typical neural network-based tandem features. We also present a new stochastic training approach for deep CCA, which produces both faster training and better-performing features.Keywords
This publication has 12 references indexed in Scilit:
- Articulatory features from deep neural networks and their role in speech recognition2014
- Multi-view learning with supervision for transformed bottleneck features2014
- Multi-view CCA-based acoustic features for phonetic recognition across speakers and domains2013
- Deep-level acoustic-to-articulatory mapping for DBN-HMM based phone recognition2012
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Connecting modalities: Semi-supervised segmentation and annotation of images using unaligned text corpora2010
- Canonical Correlation Analysis: An Overview with Application to Learning MethodsNeural Computation, 2004
- KERNEL AND NONLINEAR CANONICAL CORRELATION ANALYSISInternational Journal of Neural Systems, 2000
- Connectionist Speech Recognition1994
- Relations Between Two Sets of VariatesBiometrika, 1936