Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of making supervised speech recognition end-to-end, we introduce wav2vec-U 2.0 which does away with all audio-side pre-processing and improves accuracy through better architecture. In addition, we introduce an auxiliary self-supervised objective that ties model predictions back to the input. Experiments show that wav2vec-U 2.0 improves unsupervised recognition results across different languages while being conceptually simpler.
@article{arxiv.2204.02492,
title = {Towards End-to-end Unsupervised Speech Recognition},
author = {Alexander H. Liu and Wei-Ning Hsu and Michael Auli and Alexei Baevski},
journal= {arXiv preprint arXiv:2204.02492},
year = {2022}
}