Please use this identifier to cite or link to this item:
https://dspace.univ-ouargla.dz/jspui/handle/123456789/36703
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | BETTAYEB, Nadjla | - |
dc.contributor.author | Benettouati, Salah Eddine | - |
dc.contributor.author | Boukhetta, Mottaz Bellah | - |
dc.contributor.author | Bouzid, Mohamed laid | - |
dc.date.accessioned | 2024-09-17T10:00:41Z | - |
dc.date.available | 2024-09-17T10:00:41Z | - |
dc.date.issued | 2024 | - |
dc.identifier.citation | FACULTE DES NOUVELLES TECHNOLOGIES DE L'INFORMATIQUE ET DE LA COMMUNICATION | en_US |
dc.identifier.uri | https://dspace.univ-ouargla.dz/jspui/handle/123456789/36703 | - |
dc.description.abstract | This thesis aims to build an Arabic Text To Speech (TTS) system using the deep learning model Tacotron. The first stage consists of training an Artificial Neural Network (ANN) model able to generate audio spectrograms from a given text. The second stage transforms the generated Spectrogram into speech, using the HiFi GAN audio enhancement model. The desired goals were fully reached, as the synthesized Arabic speech received a general rate of 3.66 over 5, from the system evaluators | en_US |
dc.language.iso | en | en_US |
dc.publisher | UNIVERSITY KASDI MERBAH OUARGLA | en_US |
dc.subject | Tacotron | en_US |
dc.subject | TTS | en_US |
dc.subject | Deep Learning | en_US |
dc.subject | ANN | en_US |
dc.subject | Arabic language | en_US |
dc.title | An Arabic Text To Speech Synthesis system based on Tacotron model | en_US |
dc.type | Thesis | en_US |
Appears in Collections: | Département d'Electronique et des Télécommunications - Master |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
BEN TOUATI-BOUKHETTA-BOUZID.pdf | 2,78 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.