Completely Unsupervised Speech Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models
arXiv:1904.04100
Abstract
Producing a large annotated speech corpus for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced, but collecting a relatively big unlabeled data set for such languages is more achievable. This is why some initial effort have been reported on completely unsupervised speech recognition learned from unlabeled data only, although with relatively high error rates. In this paper, we develop a Generative Adversarial Network (GAN) to achieve this purpose, in which a Generator and a Discriminator learn from each other iteratively to improve the performance. We further use a set of Hidden Markov Models (HMMs) iteratively refined from the machine generated labels to work in harmony with the GAN. The initial experiments on TIMIT data set achieve an phone error rate of 33.1%, which is 8.5% lower than the previous state-of-the-art.
arXiv commentAccepted by Interspeech 2019
References in corpus (7)
- Efficient Estimation of Word Representations in Vector Space
- Sequence to Sequence Learning with Neural Networks
- Attention-Based Models for Speech Recognition
- Sequence Transduction with Recurrent Neural Networks
- Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces
- Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data
- Unsupervised Sequence Classification using Sequential Output Statistics