A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
Unsupervised speech recognition (unsupervised ASR) aims to learn the ASR system with non-parallel speech and text corpus only. Wav2vec-U has shown promising results in unsupervised ASR by self-supervised speech representations coupled with Generative Adversarial Network (GAN) training, but the robustness of the unsupervised ASR framework is unknown. In this work, we further analyze the training robustness of unsupervised ASR on the domain mismatch scenarios in which the domains of unpairedarXiv:2110.03509v5 fatcat:vixfqifhn5d75n22dniimdqmeu