Publication: NatiQ: An end-to-end text-to-speech system for arabic
Institution Authors
Journal Title
Journal ISSN
Volume Title
Type
Conference paper
Access
info:eu-repo/semantics/restrictedAccess
Publication Status
Published
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.
Date
2022
Publisher
Association for Computational Linguistics (ACL)