arxivst stuff from arxiv that you should probably bookmark

End to End Deep Neural Networks Radio receiver for Speech Signals

Abstract · Apr 6, 2017 23:16 ·

audio signal speech end baseband sdr quadrature lstm cs-lg cs-sd

Arxiv Abstract

  • Dan Elbaz
  • Michael Zibulevsky

End-to-end learning based approaches have been shown to be effective and are giving excellent performance for many systems with less training data. In this work we present an end to end learning approach for novel application of software defined radio (SDR) that utilizes the prior knowledge of transmitted speech message to detect and denoise the audio speech signal from the in-phase and quadrature components of its base band version.

Read the paper (pdf) »