Recurrent Neural Network Training with Dark Knowledge Transfer
This addresses the problem of data scarcity in ASR for researchers and practitioners, though it is incremental as it adapts an existing knowledge transfer method to a new teacher-child configuration.
The paper tackles the challenge of training recurrent neural networks (RNNs) with limited data in automatic speech recognition by using a deep neural network (DNN) as a teacher for knowledge transfer, achieving successful RNN training without modifications to the learning scheme.
Recurrent neural networks (RNNs), particularly long short-term memory (LSTM), have gained much attention in automatic speech recognition (ASR). Although some successful stories have been reported, training RNNs remains highly challenging, especially with limited training data. Recent research found that a well-trained model can be used as a teacher to train other child models, by using the predictions generated by the teacher model as supervision. This knowledge transfer learning has been employed to train simple neural nets with a complex one, so that the final performance can reach a level that is infeasible to obtain by regular training. In this paper, we employ the knowledge transfer learning approach to train RNNs (precisely LSTM) using a deep neural network (DNN) model as the teacher. This is different from most of the existing research on knowledge transfer learning, since the teacher (DNN) is assumed to be weaker than the child (RNN); however, our experiments on an ASR task showed that it works fairly well: without applying any tricks on the learning scheme, this approach can train RNNs successfully even with limited training data.