We propose a novel Patched Multi-Condition Training (pMCT) method for robust Automatic Speech Recognition (ASR). pMCT employs Multi-condition Audio Modification and Patching (MAMP) via mixing {\it patches} of the same utterance extracted from clean and distorted speech. Training using patch-modified signals improves robustness of models in noisy reverberant scenarios. Our proposed pMCT is evaluated on the LibriSpeech dataset showing improvement over using vanilla Multi-Condition Training (MCT). For analyses on robust ASR, we employed pMCT on the VOiCES dataset which is a noisy reverberant dataset created using utterances from LibriSpeech. In the analyses, pMCT achieves 23.1% relative WER reduction compared to the MCT.
@article{arxiv.2207.04949,
title = {pMCT: Patched Multi-Condition Training for Robust Speech Recognition},
author = {Pablo Peso Parada and Agnieszka Dobrowolska and Karthikeyan Saravanan and Mete Ozay},
journal= {arXiv preprint arXiv:2207.04949},
year = {2022}
}