Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

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

Domaine:

natural language processing

Type de record:

papermodel
Créateur:
AbdDurDemDal
Hôte:avatar
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 tts.qcri.org

Visit

arxiv.org

Tasks

speech processingtext to speech

Languages

Ga

Tags

Computation and LanguageSoundAudio and Speech Processing

Similaires

abu14/end-to-end-speech-to-textAn End-to-End Scene Text Recognition for Bilingual TextDziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian DialectEnd-to-End Text-To-Speech synthesis for under resourced South African languagesEnd-to-end Jordanian dialect speech-to-text self-supervised learning frameworkFrom Darija Speech to Standard Arabic Subtitles: An End-to-End Translation Pipeline with Whisper-FLEX

abu14/end-to-end-speech-to-text

end to end amharic text to speech voice recognition project # Amharic Speech Recognition In this p

An End-to-End Scene Text Recognition for Bilingual Text

Text localization and recognition from natural scene images has gained a lot of attention recently d

Dziri Voicebot: An End-to-End Low-Resource Speech-to-Speech Conversational System for Algerian Dialect

Automatic speech and language technologies are still heavily biased toward high-resource languages,

End-to-End Text-To-Speech synthesis for under resourced South African languages

End-to-end Jordanian dialect speech-to-text self-supervised learning framework

Speech-to-text engines are extremely needed nowadays for different applications, representing an ess

From Darija Speech to Standard Arabic Subtitles: An End-to-End Translation Pipeline with Whisper-FLEX