# ADI-20: Arabic Dialect Identification dataset and models

arXiv: https://arxiv.org/abs/2511.10070 · HTML: https://mlsanity.com/paper/2511.10070/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 13 Nov 2025.

## Builds on (most cited first, 20 of 20)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [Speech Recognition Challenge in the Wild: Arabic MGB-3](https://mlsanity.com/paper/1709.07276/) (2017)
- [Open-Source Conversational AI with SpeechBrain 1.0](https://mlsanity.com/paper/2407.00463/) (2024)
- [N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition](https://mlsanity.com/paper/2306.02902/) (2023)
- [Casablanca: Data and Models for Multidialectal Arabic Speech Recognition](https://mlsanity.com/paper/2410.04527/) (2024)
- [On the Robustness of Arabic Speech Dialect Identification](https://mlsanity.com/paper/2306.03789/) (2023)
- [Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition](https://mlsanity.com/paper/2309.11327/) (2023)
- [Yet Another Model for Arabic Dialect Identification](https://mlsanity.com/paper/2310.13812/) (2023)
- [Exploiting Dialect Identification in Automatic Dialectal Text Normalization](https://mlsanity.com/paper/2407.03020/) (2024)
- [Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect](https://mlsanity.com/paper/2407.04533/) (2024)
- [ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks](https://mlsanity.com/paper/2205.01987/) (2022)
- [Dialectal Coverage And Generalization in Arabic Speech Recognition](https://mlsanity.com/paper/2411.05872/) (2024)
- [Effects of Layer Freezing on Transferring a Speech Recognition System to Under-resourced Languages](https://mlsanity.com/paper/2102.04097/) (2021)
- [SAIDS: A Novel Approach for Sentiment Analysis Informed of Dialect and Sarcasm](https://mlsanity.com/paper/2301.02521/) (2023)
- [VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System](https://mlsanity.com/paper/2310.11069/) (2023)
- [Towards Zero-Shot Text-To-Speech for Arabic Dialects](https://mlsanity.com/paper/2406.16751/) (2024)

## Built on by (most cited first, 3 of 3)

- [CTC-DID: CTC-Based Arabic dialect identification for streaming applications](https://mlsanity.com/paper/2601.12199/) (2026)
- [NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task](https://mlsanity.com/paper/2609.27086/) (2026)
- [CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR](https://mlsanity.com/paper/2609.34481/) (2026)

## Abstract (arXiv)

We present ADI-20, an extension of the previously published ADI-17 Arabic Dialect Identification (ADI) dataset. ADI-20 covers all Arabic-speaking countries' dialects. It comprises 3,556 hours from 19 Arabic dialects in addition to Modern Standard Arabic (MSA). We used this dataset to train and evaluate various state-of-the-art ADI systems. We explored fine-tuning pre-trained ECAPA-TDNN-based models, as well as Whisper encoder blocks coupled with an attention pooling layer and a classification dense layer. We investigated the effect of (i) training data size and (ii) the model's number of parameters on identification performance. Our results show a small decrease in F1 score while using only 30% of the original training data. We open-source our collected data and trained models to enable the reproduction of our work, as well as support further research in ADI.