# Multi-Dialect Arabic Speech Recognition

arXiv: https://arxiv.org/abs/2112.14678 · HTML: https://mlsanity.com/paper/2112.14678/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 27 references that are in the map.
- First posted on arXiv 25 Dec 2021.

## Builds on (most cited first, 4 of 4)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [Deep Speech: Scaling up end-to-end speech recognition](https://mlsanity.com/paper/1412.5567/) (2014)

## Built on by (most cited first, 5 of 5)

- [Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review](https://mlsanity.com/paper/2507.07741/) (2025)
- [Munsit at NADI 2025 Shared Task 2: Pushing the Boundaries of Multidialectal Arabic ASR with Weakly Supervised Pretraining and Continual Supervised Fine-tuning](https://mlsanity.com/paper/2508.08912/) (2025)
- [VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System](https://mlsanity.com/paper/2310.11069/) (2023)
- [Bulbul: A Dataset for Dialectal Arabic Speech Recognition](https://mlsanity.com/paper/2608.21950/) (2026)
- [A Large and Diverse Arabic Corpus for Language Modeling](https://mlsanity.com/paper/2201.09227/) (2022)

## Abstract (arXiv)

This paper presents the design and development of multi-dialect automatic speech recognition for Arabic. Deep neural networks are becoming an effective tool to solve sequential data problems, particularly, adopting an end-to-end training of the system. Arabic speech recognition is a complex task because of the existence of multiple dialects, non-availability of large corpora, and missing vocalization. Thus, the first contribution of this work is the development of a large multi-dialectal corpus with either full or at least partially vocalized transcription. Additionally, the open-source corpus has been gathered from multiple sources that bring non-standard Arabic alphabets in transcription which are normalized by defining a common character-set. The second contribution is the development of a framework to train an acoustic model achieving state-of-the-art performance. The network architecture comprises of a combination of convolutional and recurrent layers. The spectrogram features of the audio data are extracted in the frequency vs time domain and fed in the network. The output frames, produced by the recurrent model, are further trained to align the audio features with its corresponding transcription sequences. The sequence alignment is performed using a beam search decoder with a tetra-gram language model. The proposed system achieved a 14% error rate which outperforms previous systems.