mlsanityData to 14 Oct 2026

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

arXiv 2206.07373 ↗First posted 15 Jun 2022cs.CL cs.SD eess.AScited by 7

Not on the map. Why?

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

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

13 of 20 references.

References · 13

  1. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  2. 2017Tacotron: Towards End-to-End Speech Synthesiscited by 490
  3. 2019Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogramcited by 340
  4. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 309
  5. 2018Adversarial Audio Synthesiscited by 225
  6. 2018Efficient Neural Audio Synthesiscited by 219
  7. 2017Speech Recognition Challenge in the Wild: Arabic MGB-3cited by 60
  8. 2019Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokenscited by 44
  9. 2020Expressive TTS Training with Frame and Style Reconstruction Losscited by 30
  10. 2018Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesiscited by 17
  11. 2020Scaling Up Online Speech Recognition Using ConvNetscited by 16
  12. 2021Arabic Speech Recognition by End-to-End, Modular Systems and Humancited by 12
1 more
  1. 2019High quality, lightweight and adaptable TTS using LPCNetcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 1; 2025: 0; 2026: 1.

7 papers.

  1. 2023LAraBench: Benchmarking Arabic AI with Large Language Modelscited by 16
  2. 2023ClArTTS: An Open-Source Classical Arabic Text-to-Speech Corpuscited by 14
  3. 2024Arabic Diacritics in the Wild: Exploiting Opportunities for Improved Diacritizationcited by 8
  4. 2023Rapid Speaker Adaptation in Low Resource Text to Speech Systems using Synthetic Data and Transfer learningcited by 2
  5. 2023QVoice: Arabic Speech Pronunciation Learning Applicationcited by 0
  6. 2023Code-Mixed Text to Speech Synthesis under Low-Resource Constraintscited by 0
  7. 2026More Data, Fewer Diacritics: Scaling Arabic TTScited by 0