Arabic Text-to-Speech (TTS) research has been hindered by the availability of both publicly available training data and accurate Arabic diacritization models. In this paper, we address the limitation by exploring Arabic TTS training on large automatically annotated data. Namely, we built a robust pipeline for collecting Arabic recordings and processing them automatically using voice activity detection, speech recognition, automatic diacritization, and noise filtering, resulting in around 4,000 hours of Arabic TTS training data. We then trained several robust TTS models with voice cloning using varying amounts of data, namely 100, 1,000, and 4,000 hours with and without diacritization. We show that though models trained on diacritized data are generally better, larger amounts of training data compensate for the lack of diacritics to a significant degree. We plan to release a public Arabic TTS model that works without the need for diacritization.
Figures & tables
Setup
Results
Diac.
Div.
Size
WER
SpeechBERT
Yes
-
4,000
1.67
0.739
Yes
-
1,000
2.55
0.729
No
-
1,000
3.12
0.726
No
-
4,000
3.18
0.732
Yes
Max
100
3.48
0.719
Table 1: Results sorted (in ascending order) by WER