43
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Deep Residual Learning for Small-Footprint Keyword Spotting

      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 explore the application of deep residual learning and dilated convolutions to the keyword spotting task, using the recently-released Google Speech Commands Dataset as our benchmark. Our best residual network (ResNet) implementation significantly outperforms Google's previous convolutional neural networks in terms of accuracy. By varying model depth and width, we can achieve compact models that also outperform previous small-footprint variants. To our knowledge, we are the first to examine these approaches for keyword spotting, and our results establish an open-source state-of-the-art reference to support the development of future speech-based interfaces.

          Related collections

          Author and article information

          Journal
          27 October 2017
          Article
          1710.10361
          f7ae0916-1fad-489b-8534-cec0ff12f431

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

          History
          Custom metadata
          5 pages, 3 figures
          cs.CL

          Comments

          Comment on this article