Review Paper for TTS Algorithm
- Author(s): Gauri S. Nandkhedkar, Prajakta A. Ghumatkar, Vinayak Kabra and Eesha Bhayya
PAPER DETAILS
- Computer Science and Engineering
-
Paper ID: UIJRTV2I70023
-
Volume: 02
-
Issue: 07
-
Pages: 197-200
-
May 2021
-
ISSN: 2582-6832
-
Views / Downloads: 633
CITE THIS
Nandkhedkar, G.S., Ghumatkar, P.A., Kabra, V. and Bhayya, E., 2021. Review Paper for TTS Algorithm. United International Journal for Research & Technology (UIJRT), 2(7), pp.197-200.
Abstract
The evolution of Text To Speech has seen many algorithms from the conventional Concatenative Synthesis to the most evolved Google’s Tacotron and its iteration Tacotron 2. This survey paper discusses the architecture and outcomes of the three recent models for TTS which are Wavenet, Tacotron 1, and Tacotron 2, and further compares all of them based on their respective mean opinion scores(MOS). The MOS Values for the above-mentioned algorithms are 4.21, 3.82, and 4.58 respectively. The paper concludes that Tacotron 2 has the highest MOS value and hence is also widely used across various applications of Text to Speech.
Keywords: Text-to-speech, Deep learning, Wavenet, Tacotron.
Related Papers
A Survey about Block Chain Technology for Machine Learning
December 5, 2022
Business Listing Application Using Laravel Framework
July 22, 2022
Web Presence of One Province in the Philippines
July 6, 2022
Increasing Damages in the Encrypted Color Image
March 16, 2022
Opinion Mining of Gujarati Language Text Using Hybrid Approach
February 25, 2022