Lattice-based training of bottleneck feature extraction neural networks


This paper investigates a method for training bottleneck (BN) features in a more targeted manner for their intended use in GMM-HMM based ASR. Our approach adds a GMM acoustic model activation layer to a standard BN feature extraction (FE) neural network and performs lattice-based MMI training on the resulting network. After training, the network is reverted… (More)


6 Figures and Tables


Citations per Year

Citation Velocity: 12

Averaging 12 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.