Data Augmentation Methods for End-to-end Speech Recognition on Distant-Talk Scenarios

TL;DR

This paper explores multiple data augmentation techniques, including TTS, Cycle-GAN, and pseudo-labeling, to enhance end-to-end speech recognition robustness in noisy distant-talk scenarios, achieving significant WER reductions.

Contribution

It introduces a novel combination of three augmentation methods to improve E2E ASR performance in challenging noisy environments.

Findings

Each augmentation method individually improves accuracy over SpecAugment.

Combining all three augmentations yields the best performance.

Achieved 4.3% WER reduction on CHiME-6 dataset.

Abstract

Although end-to-end automatic speech recognition (E2E ASR) has achieved great performance in tasks that have numerous paired data, it is still challenging to make E2E ASR robust against noisy and low-resource conditions. In this study, we investigated data augmentation methods for E2E ASR in distant-talk scenarios. E2E ASR models are trained on the series of CHiME challenge datasets, which are suitable tasks for studying robustness against noisy and spontaneous speech. We propose to use three augmentation methods and thier combinations: 1) data augmentation using text-to-speech (TTS) data, 2) cycle-consistent generative adversarial network (Cycle-GAN) augmentation trained to map two different audio characteristics, the one of clean speech and of noisy recordings, to match the testing condition, and 3) pseudo-label augmentation provided by the pretrained ASR module for smoothing label distributions. Experimental results using the CHiME-6/CHiME-4 datasets show that each augmentation method individually improves the accuracy on top of the conventional SpecAugment; further improvements are obtained by combining these approaches. We achieved 4.3\% word error rate (WER) reduction, which was more significant than that of the SpecAugment, when we combine all three augmentations for the CHiME-6 task.