High Order Recurrent Neural Networks for Acoustic Modelling

Abstract

Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the memory cells mean an LSTM layer has four times as many parameters as an RNN with the same hidden vector size. This paper addresses the vanishing gradient problem using a high order RNN (HORNN) which has additional connections from multiple previous time steps. Speech recognition experiments using British English multi-genre broadcast (MGB3) data showed that the proposed HORNN architectures for rectified linear unit and sigmoid activation functions reduced word error rates (WER) by 4.2% and 6.3% over the corresponding RNNs, and gave similar WERs to a (projected) LSTM while using only 20%--50% of the recurrent layer parameters and computation.

5 pages, 2 figures, 2 tables, to appear in 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018)

References in corpus (3)

• Pixel Recurrent Neural Networks
• Higher Order Recurrent Neural Networks
• Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition

Cited by in corpus (1)

• Semi-tied Units for Efficient Gating in LSTM and Highway Networks