Unsupervised Automatic Speech Recognition: A Review
This review addresses the problem of developing ASR for low-resource languages where labeled data is scarce, but it is incremental as it synthesizes existing research rather than presenting new findings.
The paper reviews literature to explore models and ideas for achieving fully unsupervised automatic speech recognition, aiming to identify limitations of learning from speech data alone and understand minimum requirements for ASR.
Automatic Speech Recognition (ASR) systems can be trained to achieve remarkable performance given large amounts of manually transcribed speech, but large labeled data sets can be difficult or expensive to acquire for all languages of interest. In this paper, we review the research literature to identify models and ideas that could lead to fully unsupervised ASR, including unsupervised segmentation of the speech signal, unsupervised mapping from speech segments to text, and semi-supervised models with nominal amounts of labeled examples. The objective of the study is to identify the limitations of what can be learned from speech data alone and to understand the minimum requirements for speech recognition. Identifying these limitations would help optimize the resources and efforts in ASR development for low-resource languages.