18
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A Comparison between Deep Neural Nets and Kernel Acoustic Models for Speech Recognition

      Preprint

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic models are as effective as their DNN counterparts. However, on token-error-rates DNN models can be significantly better. We have discovered that this might be attributed to DNN's unique strength in reducing both the perplexity and the entropy of the predicted posterior probabilities. Motivated by our findings, we propose a new technique, entropy regularized perplexity, for model selection. This technique can noticeably improve the recognition performance of both types of models, and reduces the gap between them. While effective on Broadcast News, this technique could be also applicable to other tasks.

          Related collections

          Author and article information

          Journal
          2016-03-18
          Article
          1603.05800
          b93b4ec3-3091-43b1-b2a5-a2da6ee321c1

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          arXiv admin note: text overlap with arXiv:1411.4000
          cs.LG stat.ML

          Machine learning,Artificial intelligence
          Machine learning, Artificial intelligence

          Comments

          Comment on this article