Neural Network (DNN) to enhance the quality and intelligibility of the noisy speech. In this
proposed model, the Voiced Speech (VS) TF mask is computed using correlogram, frame
energy and cross-channel correlogram and Unvoiced Speech (UVS) TF mask is computed
using speech onset/offset. The TF mask obtained using speech onset and offset represents
both voiced and unvoiced segment of the noisy speech signal. The UVS TF mask is …