@inproceedings{2a9d355d97374e64a68ad012ead79ad9,
title = "NatiQ: An End-to-end Text-to-Speech System for Arabic",
abstract = "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 tacotron-2) and the faster transformer model for generating mel-spectrograms from characters. We concatenated Tacotron1 with the WaveRNN vocoder, Tacotron2 with the WaveGlow vocoder and ESPnet transformer with the parallel wavegan vocoder to synthesize waveforms from the spectrograms. We used in-house speech data for two voices: 1) neutral male “Hamza”- narrating general content and news, and 2) expressive female “Amina”narrating children story books to train our models. Our best systems achieve an average Mean Opinion Score (MOS) of 4.21 and 4.40 for Amina and Hamza respectively.The objective evaluation of the systems using word and character error rate (WER and CER) as well as the response time measured by real-time factor favored the end-to-end architecture ESPnet.NatiQ demo is available online at https://tts.qcri.org.",
author = "Ahmed Abdelali and Nadir Durrani and Cenk Demiroglu and Fahim Dalvi and Hamdy Mubarak and Kareem Darwish",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 7th Arabic Natural Language Processing Workshop, WANLP 2022 held with EMNLP 2022 ; Conference date: 08-12-2022",
year = "2022",
language = "English",
series = "WANLP 2022 - 7th Arabic Natural Language Processing - Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "394--398",
booktitle = "WANLP 2022 - 7th Arabic Natural Language Processing - Proceedings of the Workshop",
address = "United States",
}