Testing three different Speech Synthesizers to acknowledge the advantages of DNN systems against HMM Methods

Authors

  • Carlos Angel Franco-Galvan Facultad de Artes, BUAP
  • José Abel Herrera-Camacho Laboratorio de Tecnologías del Lenguaje, UNAM

DOI:

https://doi.org/10.13053/cys-29-3-4517

Keywords:

Speech Synthesis, Voice Parameterization, Line Spectral Pair, Hidden Markov Models, Deep Neural Networks

Abstract

Abstract. This document reports MOS results after testing naturalness and expressiveness in three different speech synthesis systems. A first system is based on HMM, the second one combines HMM and DNN and the third one is solely based on DNN. According to the results, DNN systems outperform HMM systems in synthetic speech quality.

Author Biographies

Carlos Angel Franco-Galvan, Facultad de Artes, BUAP

Carlos Franco (Mexico 1977) is a specialist in speech synthesis. Works in Laboratorio de Tecnologías del Lenguaje UNAM and as Lecturer-Researcher in BUAP. He has several publications on Speech Synthesis in Mexican Spanish.

José Abel Herrera-Camacho, Laboratorio de Tecnologías del Lenguaje, UNAM

Abel Herrera Camacho is head of Laboratorio de Tecnologías del Lenguaje FI-UNAM. He specializes in speech synthesis and recognition and has published work on the field for over 20 years.

Downloads

Published

2025-09-25

Issue

Vol. 29 No. 3 (2025): Vol 29 No 3 (2025)

Section

Articles

License 

Hereby I transfer exclusively to the Journal "Computación y 
Sistemas", published by the Computing Research Center (CIC-IPN),
the Copyright of the aforementioned paper. I also accept that these 
rights will not be transferred to any other publication, in any other 
format, language or other existing means of developing.
I certify that the paper has not been previously disclosed or simultaneo
usly submitted to any other publication, and that it does not contain 
material whose publication would violate the Copyright or other 
proprietary rights of any person, company or institution. I certify that 
I have the permission from the institution or company where I work or 
study to publish this work.
The representative author accepts the responsibility for the publication
of this paper on behalf of each and every one of the authors. 
This transfer is subject to the following conditions:
  • The authors retain all ownership rights (such as patent rights) of this work, except for the publishing rights transferred to the CIC, through this document.
  • Authors retain the right to publish the work in whole or in part in any book they are the authors or publishers. They can also make use of this work in conferences, courses, personal web pages, and so on.
  • Authors may include working as part of his thesis, for non-profit distribution only.