{
  "id": "1711.08058",
  "version": "v1",
  "published": "2017-11-21T21:42:17.000Z",
  "updated": "2017-11-21T21:42:17.000Z",
  "title": "Multiple-Instance, Cascaded Classification for Keyword Spotting in Narrow-Band Audio",
  "authors": [
    "Ahmad AbdulKader",
    "Kareem Nassar",
    "Mohamed Mahmoud",
    "Daniel Galvez",
    "Chetan Patil"
  ],
  "comment": "To be published in the proceedings of NIPS 2017",
  "categories": [
    "cs.LG",
    "cs.CL",
    "cs.SD",
    "eess.AS"
  ],
  "abstract": "We propose using cascaded classifiers for a keyword spotting (KWS) task on narrow-band (NB), 8kHz audio acquired in non-IID environments --- a more challenging task than most state-of-the-art KWS systems face. We present a model that incorporates Deep Neural Networks (DNNs), cascading, multiple-feature representations, and multiple-instance learning. The cascaded classifiers handle the task's class imbalance and reduce power consumption on computationally-constrained devices via early termination. The KWS system achieves a false negative rate of 6% at an hourly false positive rate of 0.75",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-11-21T21:42:17.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "keyword spotting",
      "narrow-band audio",
      "cascaded classification",
      "multiple-instance",
      "state-of-the-art kws systems face"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}