Dialectal Coverage And Generalization in Arabic Speech Recognition

TL;DR

This paper presents a suite of open-source Arabic speech recognition models that effectively recognize multiple dialects, MSA, and code-switching, improving coverage and performance across diverse spoken variants.

Contribution

It introduces new multilingual and dialect-specific ASR models for Arabic, covering 17 countries and multiple dialects, with demonstrated performance improvements.

Findings

Enhanced recognition accuracy across Arabic dialects

Effective handling of code-switching scenarios

Open-source models covering diverse Arabic varieties

Abstract

Developing robust automatic speech recognition (ASR) systems for Arabic requires effective strategies to manage its diversity. Existing ASR systems mainly cover the modern standard Arabic (MSA) variety and few high-resource dialects, but fall short in coverage and generalization across the multitude of spoken variants. Code-switching with English and French is also common in different regions of the Arab world, which challenges the performance of monolingual Arabic models. In this work, we introduce a suite of ASR models optimized to effectively recognize multiple variants of spoken Arabic, including MSA, various dialects, and code-switching. We provide open-source pre-trained models that cover data from 17 Arabic-speaking countries, and fine-tuned MSA and dialectal ASR models that include at least 11 variants, as well as multi-lingual ASR models covering embedded languages in code-switched utterances. We evaluate ASR performance across these spoken varieties and demonstrate both coverage and performance gains compared to prior models.