Multimodal speaker identification

View/Open
Cita com:
hdl:2117/182658
CovenanteeUniversitat de Barcelona. Facultat de Matemàtiques i Informàtica; Universitat Rovira i Virgili. Escola Tècnica Superior d'Enginyeria
Document typeMaster thesis
Date2020-01-31
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder
Abstract
This Master Thesis (MT) describes different techniques for speaker identification. Our goal is two-fold: first to build and curate an image and audio dataset and second to use it to create a speaker recognition system.
SubjectsAutomatic speech recognition, Image recognition, Reconeixement automàtic de la parla, Reconeixement d'imatges
DegreeMÀSTER UNIVERSITARI EN INTEL·LIGÈNCIA ARTIFICIAL (Pla 2017)
Collections
Files | Description | Size | Format | View |
---|---|---|---|---|
148098.pdf | 6,325Mb | View/Open |