{"total":60,"rows":[{"id":"2105.14779","title":"Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR","created":"2021-05-31","cited_by_count":41,"area":null},{"id":"2106.13000","title":"QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpus","created":"2021-06-24","cited_by_count":38,"area":null},{"id":"2604.00688","title":"OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models","created":"2026-04-01","cited_by_count":25,"area":"diffusion"},{"id":"2306.02902","title":"N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2410.04527","title":"Casablanca: Data and Models for Multidialectal Arabic Speech Recognition","created":"2024-10-06","cited_by_count":20,"area":null},{"id":"2305.14982","title":"LAraBench: Benchmarking Arabic AI with Large Language Models","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2108.12881","title":"Investigations on Speech Recognition Systems for Low-Resource Dialectal Arabic-English Code-Switching Speech","created":"2021-08-29","cited_by_count":15,"area":null},{"id":"2211.12000","title":"ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - English","created":"2022-11-22","cited_by_count":13,"area":null},{"id":"2306.03789","title":"On the Robustness of Arabic Speech Dialect Identification","created":"2023-06-01","cited_by_count":13,"area":null},{"id":"2101.08454","title":"Arabic Speech Recognition by End-to-End, Modular Systems and Human","created":"2021-01-21","cited_by_count":12,"area":null},{"id":"2201.02550","title":"Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition","created":"2022-01-07","cited_by_count":10,"area":null},{"id":"2403.18182","title":"ZAEBUC-Spoken: A Multilingual Multidialectal Arabic-English Speech Corpus","created":"2024-03-27","cited_by_count":10,"area":null},{"id":"2107.00439","title":"What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2205.12649","title":"Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2306.15686","title":"Master-ASR: Achieving Multilingual Scalability and Low-Resource Adaptation in ASR with Modular Learning","created":"2023-06-23","cited_by_count":9,"area":null},{"id":"2206.07373","title":"NatiQ: An End-to-end Text-to-Speech System for Arabic","created":"2022-06-15","cited_by_count":7,"area":null},{"id":"2310.13812","title":"Yet Another Model for Arabic Dialect Identification","created":"2023-10-20","cited_by_count":7,"area":null},{"id":"2509.02038","title":"NADI 2025: The First Multidialectal Arabic Speech Processing Shared Task","created":"2025-09-02","cited_by_count":7,"area":null},{"id":"2106.04897","title":"Unsupervised Automatic Speech Recognition: A Review","created":"2021-06-09","cited_by_count":5,"area":null},{"id":"2505.19800","title":"MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2309.03378","title":"RoDia: A New Dataset for Romanian Dialect Identification from Speech","created":"2023-09-06","cited_by_count":4,"area":null},{"id":"2406.04512","title":"To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation","created":"2024-06-06","cited_by_count":4,"area":"distill"},{"id":"2407.01257","title":"uDistil-Whisper: Label-Free Data Filtering for Knowledge Distillation in Low-Data Regimes","created":"2024-07-01","cited_by_count":4,"area":"distill"},{"id":"2412.13788","title":"Open Universal Arabic ASR Leaderboard","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2505.20506","title":"ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2601.13319","title":"Arab Voices: Mapping Standard and Dialectal Arabic Speech Technology","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2305.07034","title":"Quran Recitation Recognition using End-to-End Deep Learning","created":"2023-05-10","cited_by_count":3,"area":null},{"id":"2310.11069","title":"VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2511.10070","title":"ADI-20: Arabic Dialect Identification dataset and models","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2601.12494","title":"Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs","created":"2026-01-18","cited_by_count":3,"area":null},{"id":"2601.13802","title":"Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis","created":"2026-01-20","cited_by_count":3,"area":null},{"id":"2312.07338","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","created":"2023-12-12","cited_by_count":2,"area":null},{"id":"2606.19747","title":"A Comparative Study of Pretrained Transformer Models for Quranic ASR: Speech Representations, Label Formats, and Dataset Composition","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2503.23576","title":"The Impact of Code-switched Synthetic Data Quality is Task Dependent: Insights from MT and ASR","created":"2025-03-30","cited_by_count":1,"area":null},{"id":"2509.14689","title":"HARNESS: Lightweight Distilled Arabic Speech Foundation Models","created":"2025-09-18","cited_by_count":1,"area":"distill"},{"id":"2509.16781","title":"MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2511.10090","title":"ELYADATA & LIA at NADI 2025: ASR and ADI Subtasks","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2601.02209","title":"ARCADE: A City-Scale Corpus for Fine-Grained Arabic Dialect Tagging","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2608.21950","title":"Bulbul: A Dataset for Dialectal Arabic Speech Recognition","created":"2026-08-22","cited_by_count":1,"area":null},{"id":"2106.04392","title":"Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2309.09443","title":"Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter","created":"2023-09-18","cited_by_count":0,"area":null},{"id":"2311.08141","title":"GMTR: Graph Matching Transformers","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2312.16805","title":"DarkShot: Lighting Dark Images with Low-Compute and High-Quality","created":"2023-12-28","cited_by_count":0,"area":null},{"id":"2401.05431","title":"TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2401.05432","title":"TEN-GUARD: Tensor Decomposition for Backdoor Attack Detection in Deep Neural Networks","created":"2024-01-06","cited_by_count":0,"area":null},{"id":"2403.13663","title":"T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image","created":"2024-03-20","cited_by_count":0,"area":null},{"id":"2408.17101","title":"Strategic Arms with Side Communication Prevail Over Low-Regret MAB Algorithms","created":"2024-08-30","cited_by_count":0,"area":null},{"id":"2410.11162","title":"Towards General Deepfake Detection with Dynamic Curriculum","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2410.13409","title":"Attr-Int: A Simple and Effective Entity Alignment Framework for Heterogeneous Knowledge Graphs","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2504.12172","title":"Poem Meter Classification of Recited Arabic Poetry: Integrating High-Resource Systems for a Low-Resource Task","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2505.24713","title":"Voice Conversion Improves Cross-Domain Robustness for Spoken Arabic Dialect Identification","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2507.06486","title":"Mask6D: Masked Pose Priors For 6D Object Pose Estimation","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2509.16438","title":"AutoArabic: A Three-Stage Framework for Localizing Video-Text Retrieval Benchmarks","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2511.18774","title":"Zero-Shot Context-Aware ASR for Diverse Arabic Varieties","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2603.08125","title":"Ramsa: A Large Sociolinguistically Rich Emirati Arabic Speech Corpus for ASR and TTS","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.14186","title":"HARNESS: Lightweight Distilled Arabic Speech Foundation Models","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2608.23421","title":"A Comprehensive Analysis of Arabic Natural Language Processing Research: Trends, Topic Evolution, and Research Gaps -- A Bibliometric and Topic-Based Study","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.27086","title":"NADI 2026: The Second Multidialectal Arabic Speech Processing Shared Task","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.34481","title":"CARDAMOM: A Micro-Dialectal Arabic Speech Dataset for ASR","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35564","title":"Almieyar: A Culturally Grounded Benchmark for Multi-Dialect Arabic Speech Recognition","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}