Unsupervised Speech Recognition

AbstractUnsupervised speech recognition ({pasted macro ‘ASRU’}/) is the problem of learning automatic speech recognition (ASR) systems from unpaired speech-only and text-only corpora. While various algorithms exist to solve this problem, …...

AbstractThe amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering …...