Cover Image

Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic AudioLLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bhatti, Hunzalah Hassan, Alam, Firoj, Chowdhury, Shammur Absar
Format:	Preprint
Published:	2026
Subjects:	Sound Artificial Intelligence Computation and Language Audio and Speech Processing 68T50 F.2.2; I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs
by: Ali, Zien Sheikh, et al.
Published: (2026)

WASIL: In-the-Wild Arabic Spoken Interactions with LLMs
by: Ali, Zien Sheikh, et al.
Published: (2026)

Beyond MCQ: An Open-Ended Arabic Cultural QA Benchmark with Dialect Variants
by: Bhatti, Hunzalah Hassan, et al.
Published: (2025)

Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages
by: Alam, Firoj, et al.
Published: (2026)

SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs
by: Alam, Firoj, et al.
Published: (2025)

CultranAI at PalmX 2025: Data Augmentation for Cultural Knowledge Representation
by: Bhatti, Hunzalah Hassan, et al.
Published: (2025)

A Unified Model For Voice and Accent Conversion In Speech and Singing using Self-Supervised Learning and Feature Extraction
by: Cheripally, Sowmya
Published: (2024)

Multi-View Multi-Task Modeling with Speech Foundation Models for Speech Forensic Tasks
by: Phukan, Orchid Chetia, et al.
Published: (2024)

Representation Loss Minimization with Randomized Selection Strategy for Efficient Environmental Fake Audio Detection
by: Phukan, Orchid Chetia, et al.
Published: (2024)

Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution
by: Phukan, Orchid Chetia, et al.
Published: (2024)

NativQA Framework: Enabling LLMs and VLMs with Native, Local, and Everyday Knowledge
by: Alam, Firoj, et al.
Published: (2025)

SARA: Stress Test Reasoning in Audio Deepfake Detection
by: Nguyen, Binh, et al.
Published: (2026)

OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA
by: Alam, Firoj, et al.
Published: (2025)

Toward Low-Latency End-to-End Voice Agents for Telecommunications Using Streaming ASR, Quantized LLMs, and Real-Time TTS
by: Ethiraj, Vignesh, et al.
Published: (2025)

GenAI Content Detection Task 2: AI vs. Human -- Academic Essay Authenticity Challenge
by: Chowdhury, Shammur Absar, et al.
Published: (2024)

Detecting Check-Worthy Claims in Political Debates, Speeches, and Interviews Using Audio Data
by: Ivanov, Petar, et al.
Published: (2023)

Strong Alone, Stronger Together: Synergizing Modality-Binding Foundation Models with Optimal Transport for Non-Verbal Emotion Recognition
by: Phukan, Orchid Chetia, et al.
Published: (2024)

Avengers Assemble: Amalgamation of Non-Semantic Features for Depression Detection
by: Phukan, Orchid Chetia, et al.
Published: (2024)

SeQuiFi: Mitigating Catastrophic Forgetting in Speech Emotion Recognition with Sequential Class-Finetuning
by: Jain, Sarthak, et al.
Published: (2024)

AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs
by: Mousi, Basel, et al.
Published: (2024)

AURA: Agent for Understanding, Reasoning, and Automated Tool Use in Voice-Driven Tasks
by: Maben, Leander Melroy, et al.
Published: (2025)

Developing Acoustic Models for Automatic Speech Recognition in Swedish
by: Salvi, Giampiero
Published: (2024)

Thaka at KSAA-2026 Task 2: Regularized Fine-Tuning for Arabic Speech Diacritization
by: Alamr, Meshal, et al.
Published: (2026)

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices
by: Lasbordes, Maxence, et al.
Published: (2025)

NativQA: Multilingual Culturally-Aligned Natural Query for LLMs
by: Hasan, Md. Arid, et al.
Published: (2024)

Deep Feed-Forward Neural Network for Bangla Isolated Speech Recognition
by: Bhadra, Dipayan, et al.
Published: (2025)

UniGlyph: A Seven-Segment Script for Universal Language Representation
by: Sherin, G. V. Bency, et al.
Published: (2024)

AudioTime: A Temporally-aligned Audio-text Benchmark Dataset
by: Xie, Zeyu, et al.
Published: (2024)

PicoAudio2: Temporal Controllable Text-to-Audio Generation with Natural Language Description
by: Zheng, Zihao, et al.
Published: (2025)

Are Music Foundation Models Better at Singing Voice Deepfake Detection? Far-Better Fuse them with Speech Foundation Models
by: Phukan, Orchid Chetia, et al.
Published: (2024)

PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation
by: Xie, Zeyu, et al.
Published: (2024)

LAraBench: Benchmarking Arabic AI with Large Language Models
by: Abdelali, Ahmed, et al.
Published: (2023)

LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking
by: Dalvi, Fahim, et al.
Published: (2023)

FakeSound: Deepfake General Audio Detection
by: Xie, Zeyu, et al.
Published: (2024)

STAR: Speech-to-Audio Generation via Representation Learning
by: Xie, Zeyu, et al.
Published: (2025)

Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMs
by: Alam, Firoj, et al.
Published: (2024)

Large Vocabulary Spontaneous Speech Recognition for Tigrigna
by: Kahsu, Ataklti, et al.
Published: (2023)

AI-based Drone Assisted Human Rescue in Disaster Environments: Challenges and Opportunities
by: Papyan, Narek, et al.
Published: (2024)

SeamlessEdit: Background Noise Aware Zero-Shot Speech Editing with in-Context Enhancement
by: Chen, Kuan-Yu, et al.
Published: (2025)

Speech Representation Analysis based on Inter- and Intra-Model Similarities
by: Kheir, Yassine El, et al.
Published: (2024)