Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR

TL;DR

This paper presents a large multilingual end-to-end speech recognition model that handles multiple languages, dialects, and code-switching scenarios, outperforming existing monolingual systems in Arabic dialectal and code-switching ASR tasks.

Contribution

The study introduces a unified self-attention based conformer model trained on Arabic, English, and French, effectively managing dialectal variation and code-switching in speech recognition.

Findings

Outperforms state-of-the-art monolingual dialectal Arabic ASR

Effective in cross-lingual and dialectal code-switching scenarios

Demonstrates robustness across multiple languages and dialects

Abstract

With the advent of globalization, there is an increasing demand for multilingual automatic speech recognition (ASR), handling language and dialectal variation of spoken content. Recent studies show its efficacy over monolingual systems. In this study, we design a large multilingual end-to-end ASR using self-attention based conformer architecture. We trained the system using Arabic (Ar), English (En) and French (Fr) languages. We evaluate the system performance handling: (i) monolingual (Ar, En and Fr); (ii) multi-dialectal (Modern Standard Arabic, along with dialectal variation such as Egyptian and Moroccan); (iii) code-switching -- cross-lingual (Ar-En/Fr) and dialectal (MSA-Egyptian dialect) test cases, and compare with current state-of-the-art systems. Furthermore, we investigate the influence of different embedding/character representations including character vs word-piece; shared vs distinct input symbol per language. Our findings demonstrate the strength of such a model by outperforming state-of-the-art monolingual dialectal Arabic and code-switching Arabic ASR.