A Robust Dialect-Aware Arabic Speech Recognition System
Document Type
Conference Proceeding
Publication Title
ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Proceedings
Abstract
Arabic is a broad language with many varieties and dialects spoken by ∼ 450 millions all around the world. Due to the linguistic diversity and variations, it is challenging to build a robust and generalized ASR system for Arabic. In this work, we address this gap by developing and demoing a system, dubbed VoxArabica, for dialect identification (DID) as well as automatic speech recognition (ASR) of Arabic. We train a wide range of models such as HuBERT (DID), Whisper, and XLS-R (ASR) in a supervised setting for Arabic DID and ASR tasks. Our DID models are trained to identify 17 different dialects in addition to MSA. We finetune our ASR models on MSA, Egyptian, Moroccan, and mixed data. Additionally, for the remaining dialects in ASR, we provide the option to choose various models such as Whisper and MMS in a zero-shot setting. We integrate these models into a single web interface with diverse features such as audio recording, file upload, model selection, and the option to raise flags for incorrect outputs. Overall, we believe VoxArabica will be useful for a wide range of audiences concerned with Arabic research. Our system is currently running at https://cdce-206-12-100-168.ngrok.io/.
First Page
441
Last Page
449
Publication Date
1-1-2023
Recommended Citation
A. Waheed et al., "A Robust Dialect-Aware Arabic Speech Recognition System," ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Proceedings, pp. 441 - 449, Jan 2023.