Diacritic recognition performance in arabic asr

H Aldarmaki, A Ghannam - ar** robust automatic speech recognition (ASR) systems for Arabic, a language
characterized by its rich dialectal diversity and often considered a low-resource language in …

Automatic Restoration of Diacritics for Speech Data Sets

S Shatnawi, S Alqahtani, H Aldarmaki - arxiv preprint arxiv:2311.10771, 2023 - arxiv.org
Automatic text-based diacritic restoration models generally have high diacritic error rates
when applied to speech transcripts as a result of domain and style shifts in spoken …

STTATTS: Unified Speech-To-Text And Text-To-Speech Model

HO Toyin, H Li, H Aldarmaki - arxiv preprint arxiv:2410.18607, 2024 - arxiv.org
Speech recognition and speech synthesis models are typically trained separately, each with
its own set of learning objectives, training data, and model parameters, resulting in two …

Data Augmentation for Speech-Based Diacritic Restoration

S Shatnawi, S Alqahtani, S Shehata… - Proceedings of The …, 2024 - aclanthology.org
This paper describes a data augmentation technique for boosting the performance of
speech-based diacritic restoration. Our experiments demonstrate the utility of this appraoch …