Analyzing Large Receptive Field Convolutional Networks for Distant Speech Recognition

TL;DR

This paper investigates large receptive field CNN architectures like dilated, recursive, and stacked hourglass networks to improve distant speech recognition, showing significant WER reductions over standard CNNs in noisy reverberant environments.

Contribution

It introduces and compares various large receptive field CNN variants for DSR, demonstrating their effectiveness over standard CNNs with fixed parameter counts.

Findings

Stacked hourglass networks reduce WER by 8.9% relative.

Large receptive field CNNs outperform standard CNNs in distant speech tasks.

Experiments confirm improvements using realistic room impulse responses.

Abstract

Despite significant efforts over the last few years to build a robust automatic speech recognition (ASR) system for different acoustic settings, the performance of the current state-of-the-art technologies significantly degrades in noisy reverberant environments. Convolutional Neural Networks (CNNs) have been successfully used to achieve substantial improvements in many speech processing applications including distant speech recognition (DSR). However, standard CNN architectures were not efficient in capturing long-term speech dynamics, which are essential in the design of a robust DSR system. In the present study, we address this issue by investigating variants of large receptive field CNNs (LRF-CNNs) which include deeply recursive networks, dilated convolutional neural networks, and stacked hourglass networks. To compare the efficacy of the aforementioned architectures with the standard CNN for Wall Street Journal (WSJ) corpus, we use a hybrid DNN-HMM based speech recognition system. We extend the study to evaluate the system performances for distant speech simulated using realistic room impulse responses (RIRs). Our experiments show that with fixed number of parameters across all architectures, the large receptive field networks show consistent improvements over the standard CNNs for distant speech. Amongst the explored LRF-CNNs, stacked hourglass network has shown improvements with a 8.9% relative reduction in word error rate (WER) and 10.7% relative improvement in frame accuracy compared to the standard CNNs for distant simulated speech signals.