Filipino to chinese speech-to-speech translator using neural network with database system

• Main Authors: Bailon, Mark Renier M., De Silva, Mark Albert C., Lapuz, Reyann Jhorel P., Tinio, John Larry A., Yu, Ted Bryan K., Gustilo, Reggie C.
• Format: text
• Published: Animo Repository 2019
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/768; https://animorepository.dlsu.edu.ph/context/faculty_research/article/1767/type/native/viewcontent
• Institution: De La Salle University

© 2019, World Academy of Research in Science and Engineering. All rights reserved. Technology nowadays becomes convenient because conveying information between computers and other electronic devices is done in a speech-to-speech environment through speech implementation. There are different technologies that can aid in speech implementation and one of which is the Neural Network System (NNS). A Neural Network System is composed of many simple processors combined together that recognizes pattern through series of trainings. The aim of the research is to produce computer software that uses an algorithm in order to translate Filipino speech into Chinese speech with the use of an artificial neural network aided by LabVIEW. The use of LabVIEW in implementing the whole speech-to-speech system organized the details through three stages: speech-to-text stage, text-to-text stage, and text-to-speech stage. The results showed that increasing the number of training of words increases the success rate of the system in recognizing the words. Some words used are nearly similar in pronunciation with other word received lower success rates as compared to unique words. Training has a success rate of 93.4% while testing yielded 91.59 percent. Speech implementation was conducted successfully that applied speech recognition, speech synthesis, and database system. The results of the speech-to-speech translation of Neural Network System in LabVIEW presented herewith such that they can be used as an aid to improvement of speech implementation.