Name
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. |
Year | Venue | Keywords |
|---|---|---|
2015 | 2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP) | multi-view learning, neural networks, deep canonical correlation analysis, XRMB, articulatory measurements |
Field | DocType | ISSN |
Kernel (linear algebra),Training set,Mel-frequency cepstrum,Pattern recognition,Feature mapping,Computer science,Canonical correlation,Speech recognition,Unsupervised learning,Artificial intelligence,Artificial neural network,Principal component analysis | Conference | 1520-6149 |
Citations | PageRank | References |
31 | 1.08 | 18 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Weiran Wang | 1 | 120 | 4.06 |
| Raman Arora | 2 | 32 | 2.12 |
| Karen Livescu | 3 | 1254 | 71.43 |
| Jeff A. Bilmes | 4 | 278 | 16.88 |