{"total":35,"rows":[{"id":"2107.01573","title":"Arabic Code-Switching Speech Recognition using Monolingual Data","created":"2021-07-04","cited_by_count":17,"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":"2310.20470","title":"Representativeness as a Forgotten Lesson for Multilingual and Code-switched Data Collection and Preparation","created":"2023-10-31","cited_by_count":16,"area":null},{"id":"2310.16621","title":"ArTST: Arabic Text and Speech Transformer","created":"2023-10-25","cited_by_count":14,"area":null},{"id":"2405.02578","title":"Mixat: A Data Set of Bilingual Emirati-English Speech","created":"2024-05-04","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":"2406.18301","title":"MSR-86K: An Evolving, Multilingual Corpus with 86,300 Hours of Transcribed Audio for Speech Recognition Research","created":"2024-06-26","cited_by_count":9,"area":null},{"id":"2311.10771","title":"Automatic Restoration of Diacritics for Speech Data Sets","created":"2023-11-15","cited_by_count":8,"area":null},{"id":"2310.07423","title":"Adapting the adapters for code-switching in multilingual ASR","created":"2023-10-11","cited_by_count":6,"area":null},{"id":"2410.03458","title":"Multi-Dialect Vietnamese: Task, Dataset, Baseline Models and Challenges","created":"2024-10-04","cited_by_count":6,"area":null},{"id":"2505.22581","title":"Tell me Habibi, is it Real or Fake?","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2304.00649","title":"Multilingual Word Error Rate Estimation: e-WER3","created":"2023-04-02","cited_by_count":5,"area":null},{"id":"2501.13419","title":"A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2510.06371","title":"OASIS: A Multilingual and Multimodal Dataset for Culturally Grounded Spoken Visual QA","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2301.09099","title":"Unsupervised Data Selection for TTS: Using Arabic Broadcast News as a Case Study","created":"2023-01-22","cited_by_count":4,"area":null},{"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":"2507.07741","title":"Code-Switching in End-to-End Automatic Speech Recognition: A Systematic Literature Review","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2406.16751","title":"Towards Zero-Shot Text-To-Speech for Arabic Dialects","created":"2024-06-24","cited_by_count":3,"area":null},{"id":"2510.10774","title":"ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis","created":"2025-10-12","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":"2602.07036","title":"MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2403.04280","title":"A New Benchmark for Evaluating Automatic Speech Recognition in the Arabic Call Domain","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2506.22143","title":"SAGE: Spliced-Audio Generated Data for Enhancing Foundational Models in Low-Resource Arabic-English Code-Switched Speech Recognition","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2603.21900","title":"Ara-Best-RQ: Multi Dialectal Arabic SSL","created":"2026-03-23","cited_by_count":2,"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":"2306.07936","title":"FOOCTTS: Generating Arabic Speech with Acoustic Environment for Football Commentator","created":"2023-06-07","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":"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":"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}],"next_cursor":null}