Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR
This addresses the problem of handling language and dialectal variation in spoken content for multilingual ASR applications, representing an incremental improvement over existing methods.
The study tackled the challenge of multilingual automatic speech recognition for Arabic, English, and French, including dialectal and code-switching variations, by designing a large multilingual end-to-end ASR using a self-attention based conformer architecture, and it outperformed state-of-the-art monolingual systems in dialectal Arabic and code-switching Arabic ASR.
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.