Poster

Unsupervised Speech Recognition

Alexei Baevski · Wei-Ning Hsu · Alexis CONNEAU · Michael Auli

Keywords: [ Adversarial Robustness and Security ] [ Deep Learning ] [ Self-Supervised Learning ] [ Generative Model ]

[ Abstract ]
Thu 9 Dec 8:30 a.m. PST — 10 a.m. PST
 
Oral presentation: Oral Session 3: Deep Learning
Wed 8 Dec 8 a.m. PST — 9 a.m. PST

Abstract:

Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U, short for wav2vec Unsupervised, a method to train speech recognition models without any labeled data. We leverage self-supervised speech representations to segment unlabeled audio and learn a mapping from these representations to phonemes via adversarial training. The right representations are key to the success of our method. Compared to the best previous unsupervised work, wav2vec-U reduces the phone error rate on the TIMIT benchmark from 26.1 to 11.3. On the larger English Librispeech benchmark, wav2vec-U achieves a word error rate of 5.9 on test-other, rivaling some of the best published systems trained on 960 hours of labeled data from only two years ago. We also experiment on nine other languages, including low-resource languages such as Kyrgyz, Swahili and Tatar.

Chat is not available.