Parameter Uncertainty for End-to-end Speech Recognition

Recent work on neural networks with probabilistic parameters has shown that parameter uncertainty improves network regularization. Parameter-specific signal-to-noise ratio (SNR) levels derived from parameter distributions were further found to have high correlations with task importance. However, most of these studies focus on tasks other than automatic speech recognition (ASR). This work investigates end-to-end models with probabilistic parameters for ASR. We demonstrate that probabilistic networks outperform conventional deterministic networks in pruning and domain adaptation experiments carried out on the Wall Street Journal and CHiME-4 datasets. We use parameter-specific SNR information to select parameters for pruning and to condition the parameter updates during adaptation. Experimental results further show that networks with lower SNR parameters (1) tolerate increased sparsity levels during parameter pruning and (2) reduce catastrophic forgetting during domain adaptation.