Highway Long Short-Term Memory RNNs for Distant Speech Recognition

Abstract

In this paper, we extend the deep long short-term memory (DLSTM) recurrent neural networks by introducing gated direct connections between memory cells in adjacent layers. These direct links, called highway connections, enable unimpeded information flow across different layers and thus alleviate the gradient vanishing problem when building deeper LSTMs. We further introduce the latency-controlled bidirectional LSTMs (BLSTMs) which can exploit the whole history while keeping the latency under control. Efficient algorithms are proposed to train these novel networks using both frame and sequence discriminative criteria. Experiments on the AMI distant speech recognition (DSR) task indicate that we can train deeper LSTMs and achieve better improvement from sequence training with highway LSTMs (HLSTMs). Our novel model obtains $43.9/47.7\%$ WER on AMI (SDM) dev and eval sets, outperforming all previous works. It beats the strong DNN and DLSTM baselines with $15.7\%$ and $5.3\%$ relative improvement respectively.

References in corpus (1)

• Improving neural networks by preventing co-adaptation of feature detectors

Cited by in corpus (8)

• Training Deep Nets with Sublinear Memory Cost
• A Comprehensive Study of Deep Bidirectional LSTM RNNs for Acoustic Modeling in Speech Recognition
• Recent Advances in Deep Learning: An Overview
• Feature-Set-Engineering for Detecting Freezing of Gait in Parkinson's Disease using Deep Recurrent Neural Networks
• Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units
• Sequence Training and Adaptation of Highway Deep Neural Networks
• Text Classification based on Multiple Block Convolutional Highways
• Educational Content Linking for Enhancing Learning Need Remediation in MOOCs