Ara-Best-RQ: Multi Dialectal Arabic SSL

• URL: http://arxiv.org/abs/2603.21900v1
• Date: Mon, 23 Mar 2026 12:23:31 GMT
• Title: Ara-Best-RQ: Multi Dialectal Arabic SSL
• Abstract summary: Ara-BEST-RQ is a family of self-supervised learning (SSL) models for Arabic speech processing.<n>We pre-train conformer-based BEST-RQ models up to 600M parameters.<n>Models are evaluated on dialect identification (DID) and automatic speech recognition (ASR) tasks.
• Score: 11.331527589218483
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Ara-BEST-RQ, a family of self-supervised learning (SSL) models specifically designed for multi-dialectal Arabic speech processing. Leveraging 5,640 hours of crawled Creative Commons speech and combining it with publicly available datasets, we pre-train conformer-based BEST-RQ models up to 600M parameters. Our models are evaluated on dialect identification (DID) and automatic speech recognition (ASR) tasks, achieving state-of-the-art performance on the former while using fewer parameters than competing models. We demonstrate that family-targeted pre-training on Arabic dialects significantly improves downstream performance compared to multilingual or monolingual models trained on non-Arabic data. All models, code, and pre-processed datasets will be publicly released to support reproducibility and further research in Arabic speech technologies.

Related papers

• Doing More with Less: Data Augmentation for Sudanese Dialect Automatic Speech Recognition [0.0]
  This paper presents a study of data augmentation techniques for fine-tuning OpenAI Whisper models.<n>It establishes the first benchmark for the Sudanese dialect.
  arXiv  Detail & Related papers  (2026-01-11T08:28:31Z)
• DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation [111.94720088481614]
  Can multimodal generative models effectively produce content given dialectal textual input?<n>We construct a new large-scale benchmark spanning six common English dialects.<n>We design a general encoder-based mitigation strategy for multimodal generative models.
  arXiv  Detail & Related papers  (2025-10-16T17:56:55Z)
• Arabic ASR on the SADA Large-Scale Arabic Speech Corpus with Transformer-Based Models [3.2669219874106608]
  We evaluate the performance of several automatic speech recognition models on a large-scale Arabic speech dataset.<n>The dataset contains 668 hours of high-quality audio from Saudi television shows.<n>We find that the MMS 1B model finetuned on SADA with a 4-gram language model achieves a WER of 40.9% and a CER of 17.6% on the SADA test clean set.
  arXiv  Detail & Related papers  (2025-08-18T14:44:25Z)
• Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis [4.774607166378613]
  Self-supervised pre-training, combined with large language models (LLM), can effectively enhance ASR performance in low-resource scenarios.<n>We pre-train a Data2vec2 model on 300,000 hours of unlabeled dialect and accented speech data and do alignment training on a supervised dataset of 40,000 hours.
  arXiv  Detail & Related papers  (2025-05-27T12:50:55Z)
• Resource-Aware Arabic LLM Creation: Model Adaptation, Integration, and Multi-Domain Testing [0.0]
  This paper presents a novel approach to fine-tuning the Qwen2-1.5B model for Arabic language processing using Quantized Low-Rank Adaptation (QLoRA) on a system with only 4GB VRAM.<n>We detail the process of adapting this large language model to the Arabic domain, using diverse datasets including Bactrian, OpenAssistant, and Wikipedia Arabic corpora.<n> Experimental results over 10,000 training steps show significant performance improvements, with the final loss converging to 0.1083.
  arXiv  Detail & Related papers  (2024-12-23T13:08:48Z)
• ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets [106.7760874400261]
  This paper presents ML-SUPERB2.0, which is a new benchmark for evaluating pre-trained SSL and supervised speech models. We find performance improvements over the setup of ML-SUPERB, but performance depends on the downstream model design. Also, we find large performance differences between languages and datasets, suggesting the need for more targeted approaches.
  arXiv  Detail & Related papers  (2024-06-12T21:01:26Z)
• Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer [59.57249127943914]
  We present a multilingual Audio-Visual Speech Recognition model incorporating several enhancements to improve performance and audio noise robustness. We increase the amount of audio-visual training data for six distinct languages, generating automatic transcriptions of unlabelled multilingual datasets. Our proposed model achieves new state-of-the-art performance on the LRS3 dataset, reaching WER of 0.8%.
  arXiv  Detail & Related papers  (2024-03-14T01:16:32Z)
• Improving Massively Multilingual ASR With Auxiliary CTC Objectives [40.10307386370194]
  We introduce our work on improving performance on FLEURS, a 102-language open ASR benchmark. We investigate techniques inspired from recent Connectionist Temporal Classification ( CTC) studies to help the model handle the large number of languages. Our state-of-the-art systems using self-supervised models with the Conformer architecture improve over the results of prior work on FLEURS by a relative 28.4% CER.
  arXiv  Detail & Related papers  (2023-02-24T18:59:51Z)
• From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition [50.93943755401025]
  We propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition. We design different auxiliary neural architectures focusing on learnable pre-trained feature enhancement. Our methods outperform existing ASR tuning architectures and their extension with self-supervised losses.
  arXiv  Detail & Related papers  (2023-01-19T02:37:56Z)
• QAmeleon: Multilingual QA with Only 5 Examples [71.80611036543633]
  We show how to leverage pre-trained language models under a few-shot learning setting. Our approach, QAmeleon, uses a PLM to automatically generate multilingual data upon which QA models are trained. Prompt tuning the PLM for data synthesis with only five examples per language delivers accuracy superior to translation-based baselines.
  arXiv  Detail & Related papers  (2022-11-15T16:14:39Z)
• Unsupervised Cross-lingual Representation Learning for Speech Recognition [63.85924123692923]
  XLSR learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations. Experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining.
  arXiv  Detail & Related papers  (2020-06-24T18:25:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.