{"total":20,"rows":[{"id":"2506.17525","title":"Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning","created":"2025-06-21","cited_by_count":11,"area":null},{"id":"2412.13788","title":"Open Universal Arabic ASR Leaderboard","created":"2024-12-18","cited_by_count":4,"area":null},{"id":"2509.07139","title":"The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2506.12615","title":"Konooz: Multi-domain Multi-dialect Corpus for Named Entity Recognition","created":"2025-06-14","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":"2604.18490","title":"LQM: Linguistically Motivated Multidimensional Quality Metrics for Machine Translation","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2504.12254","title":"Advancing Arabic Speech Recognition Through Large-Scale Weakly Supervised Learning","created":"2025-04-16","cited_by_count":2,"area":null},{"id":"2605.16364","title":"WASIL: In-the-Wild Arabic Spoken Interactions with LLMs","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2608.18689","title":"Aslema at NADI 2026: Data Augmentation for Intent Recognition and Slot Filling","created":"2026-08-19","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":"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":"2509.22808","title":"ArFake: A Robust Framework for Multi-Dialect Arabic Speech Spoofing Detection Benchmark","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2601.12199","title":"CTC-DID: CTC-Based Arabic dialect identification for streaming applications","created":"2026-01-18","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":"2603.21940","title":"SLURP-TN : Resource for Tunisian Dialect Spoken Language Understanding","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.02209","title":"CV-18 NER: Augmented Common Voice for Named Entity Recognition from Arabic Speech","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.26003","title":"Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2609.14829","title":"Enemray: Toward Capable Language Models for Hassaniya","created":"2026-09-13","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":"2609.35564","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}