Completely Unsupervised Phoneme Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models

INTERSPEECH(2019)

引用 13|浏览3
暂无评分
摘要
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.
更多
查看译文
关键词
Phoneme Recognition, Unsupervised Learning, Generative Adversarial Network, Hidden Markov Models
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络