Improved Tdnns Using Deep Kernels and Frequency Dependent Grid-RNNS
Improved Tdnns Using Deep Kernels and Frequency Dependent Grid-RNNS
Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectively model long temporal contexts. However, current TDNN models are relatively shallow, which limits the modelling capability. This paper proposes a method of …