Highway Long Short-Term Memory RNNs for Distant Speech Recognition

TL;DR

This paper introduces highway connections in deep LSTM RNNs and latency-controlled bidirectional LSTMs to improve distant speech recognition, achieving state-of-the-art results on the AMI dataset.

Contribution

The paper proposes highway connections for deeper LSTMs and latency-controlled bidirectional LSTMs, enhancing information flow and performance in distant speech recognition tasks.

Findings

Achieved 43.9/47.7% WER on AMI dataset, outperforming previous models.

Deeper LSTMs with highway connections improve sequence training results.

Latency-controlled BLSTMs effectively utilize full history with controlled delay.

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.