Harmonizing the Arabic Audio Space with Data Scheduling

• URL: http://arxiv.org/abs/2601.12494v1
• Date: Sun, 18 Jan 2026 17:08:31 GMT
• Title: Harmonizing the Arabic Audio Space with Data Scheduling
• Authors: Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury,
• Abstract summary: This paper presents the first systematic study of multi-task instruction tuning for an Arabic-centric audio LLM.<n>We fine-tune Qwen2.5- Omni (7B) and propose Task-Progressive Curriculum (TPC) along with Aligner-Based Diverse Sampling (ADS)<n>Our results reveal a critical efficiency, robustness trade-off: while ADS accelerates initial convergence, its inherent gradient volatility can destabilize generative decoding under prolonged training.
• Score: 15.84874997729878
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Audio large language models (LLMs) enable unified speech understanding and generation, yet their adaptation to linguistically complex, dialect-rich settings remains underexplored. This paper presents the first systematic study of multi-task instruction tuning for an Arabic-centric audio LLM, covering a hierarchy of generative tasks (ASR, speech summarization) and discriminative tasks (dialect and emotion identification). To support this study, we introduce AraMega-SSum, a novel dataset for Arabic speech summarization. We fine-tune Qwen2.5-Omni (7B) and propose Task-Progressive Curriculum (TPC) along with Aligner-Based Diverse Sampling (ADS), a strategy that constructs information-dense batches by selecting task- and label-balanced examples. Our results reveal a critical efficiency, robustness trade-off: while ADS accelerates initial convergence and boosts paralinguistic F1-scores, its inherent gradient volatility can destabilize generative decoding under prolonged training. Furthermore, while the TPC stabilizes core acoustic mapping, it often induces negative transfer in downstream tasks. We demonstrate that a Hybrid TPC+ADS Strategy provides an optimal training ``recipe'', first establishing a robust representative foundation before employing diversity-aware refinement to capture fine-grained nuances. These findings offer practical guidance for the efficient adaptation of Omni-models in complex, low-resource multimodal environments.

Related papers

• SpidR-Adapt: A Universal Speech Representation Model for Few-Shot Adaptation [40.55805997909858]
  We introduce SpidR-Adapt for rapid adaptation to new languages using minimal unlabeled data.<n>We construct a multi-task adaptive pre-training protocol which formulates the adaptation process as a bi-level optimization framework.<n> Empirically, SpidR-Adapt achieves rapid gains in phonemic discriminability and spoken language modeling.
  arXiv  Detail & Related papers  (2025-12-24T14:33:16Z)
• Session-Level Spoken Language Assessment with a Multimodal Foundation Model via Multi-Target Learning [8.717610965852037]
  Spoken Language Assessment (SLA) estimates a learner's oral proficiency from spontaneous speech.<n>This paper introduces a novel multimodal foundation model approach that performs session-level evaluation in a single pass.
  arXiv  Detail & Related papers  (2025-09-19T14:33:05Z)
• Munsit at NADI 2025 Shared Task 2: Pushing the Boundaries of Multidialectal Arabic ASR with Weakly Supervised Pretraining and Continual Supervised Fine-tuning [0.0]
  We present a scalable training pipeline that combines weakly supervised learning with supervised fine-tuning to develop a robust Arabic ASR model.<n>Our approach achieves state-of-the-art results, ranking first in the multi-dialectal Arabic ASR challenge.
  arXiv  Detail & Related papers  (2025-08-12T13:02:22Z)
• DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment [94.0709779805955]
  We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM)<n>It is designed for robust auditory perception and instruction-following, without requiring task-specific audio instruction-tuning.<n>DeSTA2.5-Audio achieves state-of-the-art or competitive performance across a wide range of audio-language benchmarks.
  arXiv  Detail & Related papers  (2025-07-03T16:28:25Z)
• Multi-task Learning with Active Learning for Arabic Offensive Speech Detection [1.534667887016089]
  This paper proposes a novel framework that integrates multi-task learning (MTL) with active learning to enhance offensive speech detection in Arabic social media text.<n>Our approach dynamically adjusts task weights during training to balance the contribution of each task and optimize performance.<n> Experimental results on the OSACT2022 dataset show that the proposed framework achieves a state-of-the-art macro F1-score of 85.42%.
  arXiv  Detail & Related papers  (2025-06-03T11:17:03Z)
• From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data [55.2480439325792]
  Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs.<n>These models are typically adapted from text-based large language models (LLMs) through additional training on audio-related tasks.<n>We propose a data generation framework that produces contrastive-like training data, designed to enhance ALLMs' ability to differentiate between present and absent sounds.
  arXiv  Detail & Related papers  (2025-05-26T16:08:41Z)
• Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs [3.8300818830608345]
  Multi-modal contrastive learning strategies for audio and text have rapidly gained interest.<n>The ability of these models to understand natural language and temporal relations is still a largely unexplored and open field for research.<n>We propose to equip the multi-modal ALMs with temporal understanding without loosing their inherent prior capabilities of audio-language tasks with a temporal instillation method TeminAL.
  arXiv  Detail & Related papers  (2024-08-17T18:53:17Z)
• WavLLM: Towards Robust and Adaptive Speech Large Language Model [93.0773293897888]
  We introduce WavLLM, a robust and adaptive speech large language model with dual encoders, and a prompt-aware LoRA weight adapter. We validate the proposed model on universal speech benchmarks including tasks such as ASR, ST, SV, ER, and also apply it to specialized datasets like Gaokao English listening comprehension set for SQA, and speech Chain-of-Thought (CoT) evaluation set.
  arXiv  Detail & Related papers  (2024-03-31T12:01:32Z)
• Large Language Models are Efficient Learners of Noise-Robust Speech Recognition [65.95847272465124]
  Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR) In this work, we extend the benchmark to noisy conditions and investigate if we can teach LLMs to perform denoising for GER. Experiments on various latest LLMs demonstrate our approach achieves a new breakthrough with up to 53.9% correction improvement in terms of word error rate.
  arXiv  Detail & Related papers  (2024-01-19T01:29:27Z)
• End-to-End Active Speaker Detection [58.7097258722291]
  We propose an end-to-end training network where feature learning and contextual predictions are jointly learned. We also introduce intertemporal graph neural network (iGNN) blocks, which split the message passing according to the main sources of context in the ASD problem. Experiments show that the aggregated features from the iGNN blocks are more suitable for ASD, resulting in state-of-the art performance.
  arXiv  Detail & Related papers  (2022-03-27T08:55:28Z)
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing [102.45426364965887]
  We propose a new pre-trained model, WavLM, to solve full-stack downstream speech tasks. WavLM is built based on the HuBERT framework, with an emphasis on both spoken content modeling and speaker identity preservation. We scale up the training dataset from 60k hours to 94k hours of public audio data, and optimize its training procedure for better representation extraction.
  arXiv  Detail & Related papers  (2021-10-26T17:55:19Z)

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.