Training unsupervised speech recognition systems presents challenges due to GAN-associated instability, misalignment between speech and text, and significant memory demands. To tackle these challenges, we introduce a novel ASR system, ESPUM. This system harnesses the power of lower-order N-skipgrams (up to N=3) combined with positional unigram statistics gathered from a small batch of samples. Evaluated on the TIMIT benchmark, our model showcases competitive performance in ASR and phoneme segmentation tasks. Access our publicly available code at https://github.com/lwang114/GraphUnsupASR.
@article{arxiv.2310.02382,
title = {Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching},
author = {Liming Wang and Mark Hasegawa-Johnson and Chang D. Yoo},
journal= {arXiv preprint arXiv:2310.02382},
year = {2023}
}