Open AccessLanguage to language Translation using GRU method
Publication year - 2020
Publication title -
journal of science and technolgy
Language(s) - English
Resource type - Journals
ISSN - 2456-5660
DOI - 10.46243/jst.2020.v5.i3.pp192-194
Subject(s) - computer science , natural language processing , speech recognition , speech translation , artificial intelligence , transcoding , pitch accent , speech synthesis , interpretation (philosophy) , set (abstract data type) , representation (politics) , artificial neural network , speech corpus , process (computing) , machine translation , prosody , computer network , politics , political science , law , programming language , operating system
Current state of the art translation systems for speech to speech rely heavily on a text representation forthe interpretation. By transcoding speech to text we lose important information about the characteristics of the voicelike the emotion, pitch and accent. The thesis examine the likelihood of using an GRU neural network model totranslate speech to speech without the requirement of a text representation that's by translating using the raw audiodata directly so as to persevere the characteristics of the voice that otherwise stray within the text transcoding apart of the interpretation process. As a part of the research we create an information set of phrases suitable forspeech to speech translation tasks. The thesis leads to a signal of concept system which requires scaling theunderlying deep neural network so as to figure better.