Automatic Speech Recognition And Limited Vocabulary: A Survey

TL;DR

This survey reviews mechanisms, techniques, and future directions for automatic speech recognition systems that focus on limited vocabulary, emphasizing their importance for under-resourced languages and diverse applications.

Contribution

It provides a comprehensive overview of ASR methods for limited vocabulary, highlighting recent advances and future research directions in this specialized area.

Findings

Most tools for limited vocabulary ASR are applicable to general ASR systems.

Limited vocabulary ASR aids under-resourced language preservation.

Recent techniques improve accuracy in low-resource settings.

Abstract

Automatic Speech Recognition (ASR) is an active field of research due to its large number of applications and the proliferation of interfaces or computing devices that can support speech processing. However, the bulk of applications are based on well-resourced languages that overshadow under-resourced ones. Yet, ASR represents an undeniable means to promote such languages, especially when designing human-to-human or human-to-machine systems involving illiterate people. An approach to design an ASR system targeting under-resourced languages is to start with a limited vocabulary. ASR using a limited vocabulary is a subset of the speech recognition problem that focuses on the recognition of a small number of words or sentences. This paper aims to provide a comprehensive view of mechanisms behind ASR systems as well as techniques, tools, projects, recent contributions, and possible future directions in ASR using a limited vocabulary. This work consequently provides a way forward when designing an ASR system using limited vocabulary. Although an emphasis is put on limited vocabulary, most of the tools and techniques reported in this survey can be applied to ASR systems in general.