Speaker cluster-based speaker adaptive training for deep neural network acoustic modeling

  • Wei Chu, Ruxin Chen
  • Published 2016 in
    2016 IEEE International Conference on Acoustics…


A speaker cluster-based speaker adaptive training (SAT) method under deep neural network-hidden Markov model (DNN-HMM) framework is presented in this paper. During training, speakers that are acoustically adjacent to each other are hierarchically clustered using an i-vector based distance metric. DNNs with speaker dependent layers are then adaptively… (More)
DOI: 10.1109/ICASSP.2016.7472688

3 Figures and Tables


  • Presentations referencing similar topics