Publication:
NatiQ: An end-to-end text-to-speech system for arabic

Placeholder

Institution Authors

Research Projects

Journal Title

Journal ISSN

Volume Title

Type

Conference paper

Access

info:eu-repo/semantics/restrictedAccess

Publication Status

Published

Journal Issue

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)

Description

Keywords

Citation

Collections


Page Views

0

File Download

0