Back to Search Start Over

Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching

Authors :
Wang, Liming
Hasegawa-Johnson, Mark
Yoo, Chang D.
Publication Year :
2023

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.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2310.02382
Document Type :
Working Paper