# On the Robustness of Arabic Speech Dialect Identification

arXiv: https://arxiv.org/abs/2306.03789 · HTML: https://mlsanity.com/paper/2306.03789/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 1 Jun 2023.

## Builds on (most cited first, 15 of 15)

- [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)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale](https://mlsanity.com/paper/2111.09296/) (2021)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [pyannote.audio: neural building blocks for speaker diarization](https://mlsanity.com/paper/1911.01255/) (2019)
- [VoxLingua107: a Dataset for Spoken Language Recognition](https://mlsanity.com/paper/2011.12998/) (2020)
- [End-to-end speaker segmentation for overlap-aware resegmentation](https://mlsanity.com/paper/2104.04045/) (2021)
- [Speech Recognition Challenge in the Wild: Arabic MGB-3](https://mlsanity.com/paper/1709.07276/) (2017)
- [Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System](https://mlsanity.com/paper/1804.05160/) (2018)
- [Improved Speech Representations with Multi-Target Autoregressive Predictive Coding](https://mlsanity.com/paper/2004.05274/) (2020)
- [MIT-QCRI Arabic Dialect Identification System for the 2017 Multi-Genre Broadcast Challenge](https://mlsanity.com/paper/1709.00387/) (2017)
- [Transformer-based Arabic Dialect Identification](https://mlsanity.com/paper/2011.00699/) (2020)
- [Insights into End-to-End Learning Scheme for Language Identification](https://mlsanity.com/paper/1804.00381/) (2018)
- [UTD-CRSS Submission for MGB-3 Arabic Dialect Identification: Front-end and Back-end Advancements on Broadcast Speech](https://mlsanity.com/paper/1710.00113/) (2017)

## Built on by (most cited first, 13 of 13)

- [NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2407.04910/) (2024)
- [Casablanca: Data and Models for Multidialectal Arabic Speech Recognition](https://mlsanity.com/paper/2410.04527/) (2024)
- [ArTST: Arabic Text and Speech Transformer](https://mlsanity.com/paper/2310.16621/) (2023)
- [Yet Another Model for Arabic Dialect Identification](https://mlsanity.com/paper/2310.13812/) (2023)
- [NADI 2025: The First Multidialectal Arabic Speech Processing Shared Task](https://mlsanity.com/paper/2509.02038/) (2025)
- [Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe](https://mlsanity.com/paper/2508.01691/) (2025)
- [Arab Voices: Mapping Standard and Dialectal Arabic Speech Technology](https://mlsanity.com/paper/2601.13319/) (2026)
- [VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System](https://mlsanity.com/paper/2310.11069/) (2023)
- [ADI-20: Arabic Dialect Identification dataset and models](https://mlsanity.com/paper/2511.10070/) (2025)
- [Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification](https://mlsanity.com/paper/2505.24713/) (2025)
- [On Barriers to Archival Audio Processing](https://mlsanity.com/paper/2507.08768/) (2025)
- [Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion](https://mlsanity.com/paper/2607.02862/) (2026)
- [NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task](https://mlsanity.com/paper/2609.27086/) (2026)

## Abstract (arXiv)

Arabic dialect identification (ADI) tools are an important part of the large-scale data collection pipelines necessary for training speech recognition models. As these pipelines require application of ADI tools to potentially out-of-domain data, we aim to investigate how vulnerable the tools may be to this domain shift. With self-supervised learning (SSL) models as a starting point, we evaluate transfer learning and direct classification from SSL features. We undertake our evaluation under rich conditions, with a goal to develop ADI systems from pretrained models and ultimately evaluate performance on newly collected data. In order to understand what factors contribute to model decisions, we carry out a careful human study of a subset of our data. Our analysis confirms that domain shift is a major challenge for ADI models. We also find that while self-training does alleviate this challenges, it may be insufficient for realistic conditions.