Unsupervised Automatic Speech Recognition: A Review

Abstract

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.

26 pages + 10 pages of references, 3 figures. Speech Communication (2022)

References in corpus (9)

• Hierarchical Multiscale Recurrent Neural Networks
• Wav2Letter: an End-to-End ConvNet-based Speech Recognition System
• An Unsupervised Autoregressive Model for Speech Representation Learning
• Unsupervised Speech Recognition
• The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
• A Fully Differentiable Beam Search Decoder
• A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
• Analyzing the Robustness of Unsupervised Speech Recognition
• Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching

Cited by in corpus (1)

• Automatic Speech Recognition using Advanced Deep Learning Approaches: A survey