25 citations · 28 across the 6 of their papers we have counts for
6 papers
Towards Zero-Shot Text-To-Speech for Arabic Dialects
Khai Duy Doan, Abdul Waheed, Muhammad Abdul-Mageed
Zero-shot multi-speaker text-to-speech (ZS-TTS) systems have advanced for English, however, it still lags behind due to insufficient resources. We address this gap for Arabic, a la…
To Distill or Not to Distill? On the Robustness of Robust Knowledge Distillation
Abdul Waheed, Karima Kadaoui, Muhammad Abdul-Mageed
Arabic is known to present unique challenges for Automatic Speech Recognition (ASR). On one hand, its rich linguistic diversity and wide range of dialects complicate the developmen…
VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System
Abdul Waheed, Bashar Talafha, Peter Sullivan +2
Arabic is a complex language with many varieties and dialects spoken by over 450 millions all around the world. Due to the linguistic diversity and variations, it is challenging to…
TARJAMAT: Evaluation of Bard and ChatGPT on Machine Translation of Ten Arabic Varieties
Karima Kadaoui, Samar M. Magdy, Abdul Waheed +4
Despite the purported multilingual proficiency of instruction-finetuned large language models (LLMs) such as ChatGPT and Bard, the linguistic inclusivity of these models remains in…
N-Shot Benchmarking of Whisper on Diverse Arabic Speech Recognition
Bashar Talafha, Abdul Waheed, Muhammad Abdul-Mageed
Whisper, the recently developed multilingual weakly supervised model, is reported to perform well on multiple speech recognition benchmarks in both monolingual and multilingual set…
LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions
Minghao Wu, Abdul Waheed, Chiyu Zhang +2
Large language models (LLMs) with instruction fine-tuning demonstrate superior generative capabilities. However, these models are resource-intensive. To alleviate this issue, we ex…