Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review

TL;DR

This paper systematically reviews end-to-end automatic speech recognition models for code-switching, analyzing current research, datasets, challenges, and gaps to guide future advancements in multilingual speech recognition.

Contribution

It provides a comprehensive analysis of existing literature on code-switching in end-to-end ASR, highlighting research trends, datasets, and challenges.

Findings

Identification of key datasets and metrics used in the field

Discussion of challenges unique to code-switching in ASR

Insights into research gaps and future directions

Abstract

Motivated by a growing research interest into automatic speech recognition (ASR), and the growing body of work for languages in which code-switching (CS) often occurs, we present a systematic literature review of code-switching in end-to-end ASR models. We collect and manually annotate papers published in peer reviewed venues. We document the languages considered, datasets, metrics, model choices, and performance, and present a discussion of challenges in end-to-end ASR for code-switching. Our analysis thus provides insights on current research efforts and available resources as well as opportunities and gaps to guide future research.