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.

Stats

• citations13
• S2 citations—
• github stars0
• HF likes0
• heat score8.60
• arxiv keyzhang2018high

Related papers

• Learning Compact Recurrent Neural Networks (2016)0.00
• Memory Visualization For Gated Recurrent Neural Networks In Speech Recognition (2016)11.76
• Gated Recurrent Unit Based Acoustic Modeling With Future Context (2018)7.16
• A Comparison Of Adaptation Techniques And Recurrent Neural Network Architectures (2018)3.58
• Long Short-term Memory Based Convolutional Recurrent Neural Networks For Large Vocabulary Speech Recognition (2016)6.77
• Rhr-net: A Residual Hourglass Recurrent Neural Network For Speech Enhancement (2019)0.00
• Improving Speech Recognition By Revising Gated Recurrent Units (2017)11.19
• Investigating Gated Recurrent Neural Networks For Speech Synthesis (2016)0.00