Document Type

Article

Publication Title

Speech Communication

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 sub-word and word modeling, unsupervised segmentation of the speech signal, and unsupervised mapping from speech segments to text. 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. © 2022 The Author(s)

First Page

76

Last Page

91

DOI

10.1016/j.specom.2022.02.005

Publication Date

4-2022

Keywords

Mapping, Speech, Automatic speech recognition, Automatic speech recognition system, Cross-modal, Cross-modal mapping, Data set, Labeled data, Large amounts, Performance, Speech segmentation, Unsupervised automatic speech recognition, Speech recognition

Comments

Hybrid Gold Open Access

Archived, thanks to Elsevier ScienceDirect

License: CC BY NC-ND 4.0

Uploaded 29 November 2023

Download

Share

COinS