# NatiQ: An End-to-end Text-to-Speech System for Arabic

arXiv: https://arxiv.org/abs/2206.07373 · HTML: https://mlsanity.com/paper/2206.07373/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 15 Jun 2022.

## Builds on (most cited first, 13 of 13)

- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Adversarial Audio Synthesis](https://mlsanity.com/paper/1802.04208/) (2018)
- [Efficient Neural Audio Synthesis](https://mlsanity.com/paper/1802.08435/) (2018)
- [Speech Recognition Challenge in the Wild: Arabic MGB-3](https://mlsanity.com/paper/1709.07276/) (2017)
- [Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens](https://mlsanity.com/paper/1910.11997/) (2019)
- [Expressive TTS Training with Frame and Style Reconstruction Loss](https://mlsanity.com/paper/2008.01490/) (2020)
- [Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis](https://mlsanity.com/paper/1807.06736/) (2018)
- [Scaling Up Online Speech Recognition Using ConvNets](https://mlsanity.com/paper/2001.09727/) (2020)
- [Arabic Speech Recognition by End-to-End, Modular Systems and Human](https://mlsanity.com/paper/2101.08454/) (2021)
- [High quality, lightweight and adaptable TTS using LPCNet](https://mlsanity.com/paper/1905.00590/) (2019)

## Built on by (most cited first, 7 of 7)

- [LAraBench: Benchmarking Arabic AI with Large Language Models](https://mlsanity.com/paper/2305.14982/) (2023)
- [ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpus](https://mlsanity.com/paper/2303.00069/) (2023)
- [Arabic Diacritics in the Wild: Exploiting Opportunities for Improved Diacritization](https://mlsanity.com/paper/2406.05760/) (2024)
- [Rapid Speaker Adaptation in Low Resource Text to Speech Systems using Synthetic Data and Transfer learning](https://mlsanity.com/paper/2312.01107/) (2023)
- [QVoice: Arabic Speech Pronunciation Learning Application](https://mlsanity.com/paper/2305.07445/) (2023)
- [Code-Mixed Text to Speech Synthesis under Low-Resource Constraints](https://mlsanity.com/paper/2312.01103/) (2023)
- [More Data, Fewer Diacritics: Scaling Arabic TTS](https://mlsanity.com/paper/2603.01622/) (2026)

## Abstract (arXiv)

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 on-line at https://tts.qcri.org