Unsupervised Speech Recognition with N-skipgram and Positional Unigram Matching

Liming Wang; Mark Hasegawa-Johnson; Chang D. Yoo

ICASSP 2024accepted0 citations

Unsupervised Speech Recognition with N-skipgram and Positional Unigram Matching

Liming Wang, Mark Hasegawa-Johnson, Chang D. Yoo

Abstract

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.

BibTeX

@inproceedings{icassp2024_unsupervisedspee,
  title = {Unsupervised Speech Recognition with N-skipgram and Positional Unigram Matching},
  author = {Liming Wang and Mark Hasegawa-Johnson and Chang D. Yoo},
  booktitle = {ICASSP 2024},
  year = {2024}
}