Unsupervised Speech Recognition

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 phoneme 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.

References in corpus (10)

• Sequence to Sequence Learning with Neural Networks
• Attention-Based Models for Speech Recognition
• Sequence Transduction with Recurrent Neural Networks
• Dual Learning for Machine Translation
• MLS: A Large-Scale Multilingual Dataset for Speech Research
• vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations
• Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
• Improving Transformer-based Speech Recognition Using Unsupervised Pre-training
• Semi-Supervised Speech Recognition via Local Prior Matching
• Differentiable Weighted Finite-State Transducers

Cited by in corpus (10)

• Unsupervised Automatic Speech Recognition: A Review
• SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training
• PARP: Prune, Adjust and Re-Prune for Self-Supervised Speech Recognition
• Accent-Robust Automatic Speech Recognition Using Supervised and Unsupervised Wav2vec Embeddings
• Simple and Effective Zero-shot Cross-lingual Phoneme Recognition
• UniSpeech at scale: An Empirical Study of Pre-training Method on Large-Scale Speech Recognition Dataset
• Comparison of Self-Supervised Speech Pre-Training Methods on Flemish Dutch
• NWT: Towards natural audio-to-video generation with representation learning
• Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?
• Towards an Efficient Voice Identification Using Wav2Vec2.0 and HuBERT Based on the Quran Reciters Dataset