English

Towards End-to-end Unsupervised Speech Recognition

Computation and Language 2022-06-16 v2 Sound Audio and Speech Processing

Abstract

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.

Keywords

Cite

@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}
}

Comments

Preprint

R2 v1 2026-06-24T10:39:09.067Z