3-D Acoustic Modeling For Far-Field Multi-Channel Speech Recognition

The conventional approach to automatic speech recognition in multi-channel reverberant conditions involves a beamforming based enhancement of the multi-channel speech signal followed by a single channel neural acoustic model. In this paper, we propose to
  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00

Videos in this product