Residual Convolutional CTC Networks for Automatic Speech Recognition

TL;DR

This paper introduces a deep residual CNN architecture with CTC loss for improved automatic speech recognition, demonstrating significant error rate reductions on benchmark datasets.

Contribution

The paper proposes a novel deep residual CNN architecture with CTC loss for end-to-end speech recognition, and introduces a CTC-based system combination method.

Findings

Achieved lowest WER on WSJ and Tencent Chat datasets.

System combination further reduced error rates.

Demonstrated effectiveness of deep residual CNNs in ASR.

Abstract

Deep learning approaches have been widely used in Automatic Speech Recognition (ASR) and they have achieved a significant accuracy improvement. Especially, Convolutional Neural Networks (CNNs) have been revisited in ASR recently. However, most CNNs used in existing work have less than 10 layers which may not be deep enough to capture all human speech signal information. In this paper, we propose a novel deep and wide CNN architecture denoted as RCNN-CTC, which has residual connections and Connectionist Temporal Classification (CTC) loss function. RCNN-CTC is an end-to-end system which can exploit temporal and spectral structures of speech signals simultaneously. Furthermore, we introduce a CTC-based system combination, which is different from the conventional frame-wise senone-based one. The basic subsystems adopted in the combination are different types and thus mutually complementary to each other. Experimental results show that our proposed single system RCNN-CTC can achieve the lowest word error rate (WER) on WSJ and Tencent Chat data sets, compared to several widely used neural network systems in ASR. In addition, the proposed system combination can offer a further error reduction on these two data sets, resulting in relative WER reductions of $14.91\%$ and $6.52\%$ on WSJ dev93 and Tencent Chat data sets respectively.