86 citations · 258 across the 18 of their papers we have counts for
4 papers · 1 filter
Post-hoc analysis of Arabic transformer models
Ahmed Abdelali, Nadir Durrani, Fahim Dalvi +1
Arabic is a Semitic language which is widely spoken with many dialects. Given the success of pre-trained language models, many transformer models trained on Arabic and its dialects…
NatiQ: An End-to-end Text-to-Speech System for Arabic
Ahmed Abdelali, Nadir Durrani, Cenk Demiroglu +3
NatiQ is end-to-end text-to-speech system for Arabic. Our speech synthesizer uses an encoder-decoder architecture with attention. We used both tacotron-based models (tacotron-1 and…
Interpreting Arabic Transformer Models
Ahmed Abdelali, Nadir Durrani, Fahim Dalvi +1
Arabic is a Semitic language which is widely spoken with many dialects. Given the success of pre-trained language models, many transformer models trained on Arabic and its dialects…
Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition
Amir Hussein, Shammur Absar Chowdhury, Ahmed Abdelali +3
The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language. Designing a CS-ASR system has many…