10.1184/R1/6473306.v1
Yajie Miao
Yajie
Miao
Florian Metze
Florian
Metze
Shourabh Rawat
Shourabh
Rawat
Deep maxout networks for low-resource speech recognition
Carnegie Mellon University
2013
Deep maxout networks
speech recognition
low-resource conditions
deep learning
2013-12-01 00:00:00
Journal contribution
https://kilthub.cmu.edu/articles/journal_contribution/Deep_maxout_networks_for_low-resource_speech_recognition/6473306
<p>As a feed-forward architecture, the recently proposed maxout networks integrate dropout naturally and show state-of-the-art results on various computer vision datasets. This paper investigates the application of deep maxout networks (DMNs) to large vocabulary continuous speech recognition (LVCSR) tasks. Our focus is on the particular advantage of DMNs under low-resource conditions with limited transcribed speech. We extend DMNs to hybrid and bottleneck feature systems, and explore optimal network structures (number of maxout layers, pooling strategy, etc) for both setups. On the newly released Babel corpus, behaviors of DMNs are extensively studied under different levels of data availability. Experiments show that DMNs improve low-resource speech recognition significantly. Moreover, DMNs introduce sparsity to their hidden activations and thus can act as sparse feature extractors.</p>