[2603.02368] RO-N3WS: Enhancing Generalization in Low-Resource ASR with Diverse Romanian Speech Benchmarks

Computer Science > Computation and Language arXiv:2603.02368 (cs) [Submitted on 2 Mar 2026] Title:RO-N3WS: Enhancing Generalization in Low-Resource ASR with Diverse Romanian Speech Benchmarks Authors:Alexandra Diaconu, Mădălina Vînaga, Bogdan Alexe View a PDF of the paper titled RO-N3WS: Enhancing Generalization in Low-Resource ASR with Diverse Romanian Speech Benchmarks, by Alexandra Diaconu and 2 other authors View PDF HTML (experimental) Abstract:We introduce RO-N3WS, a benchmark Romanian speech dataset designed to improve generalization in automatic speech recognition (ASR), particularly in low-resource and out-of-distribution (OOD) conditions. RO-N3WS comprises over 126 hours of transcribed audio collected from broadcast news, literary audiobooks, film dialogue, children's stories, and conversational podcast speech. This diversity enables robust training and fine-tuning across stylistically distinct domains. We evaluate several state-of-the-art ASR systems (Whisper, Wav2Vec 2.0) in both zero-shot and fine-tuned settings, and conduct controlled comparisons using synthetic data generated with expressive TTS models. Our results show that even limited fine-tuning on real speech from RO-N3WS yields substantial WER improvements over zero-shot baselines. We will release all models, scripts, and data splits to support reproducible research in multilingual ASR, domain adaptation, and lightweight deployment. Subjects: Computation and Language (cs.CL); Machine Learning (cs.LG); ...