Wang, L., Chang, K.-W., Kashino, K., Harwath, D., Hasegawa-Johnson, M., & Glass, J. R. (2026). Unsupervised Speech Recognition at the Syllable Level (arXiv:2608.22907). arXiv. https://doi.org/10.48550/arXiv.2608.22907
arXiv.org
Unsupervised Speech Recognition at the Syllable Level
Training speech recognizers with unpaired speech and text -- known as unsupervised speech recognition (UASR) -- is a crucial step toward extending ASR to low-resource languages in the long-tail...
August 31, 2026 127 1
