Abstract
This paper presents the method of applying speaker-independent and bidirectional speech-to-speech translation system for spontaneous dialogs in real time calling system. This technique recognizes spoken input, analyzes and translates it, and finally utters the translation. The major part of Speech translation comes under Natural language processing. Natural language processing is a branch of Artificial Intelligence that deals with analyzing, understanding and generating the languages that humans use naturally in order to interface with computers in both written and spoken contexts using natural human languages instead of computer languages. Speech Translation involves techniques to translate the spoken sentences from one language to another. The major part of speech translation involves Speech Recognition which is the translation of spoken speech to text and identifying the context and linguistic structure of the input speech. In the current scenario, the machine does not identify whether the given word is in past tense or present tense. By using the algorithm, we search for a word to check if it is past or present by searching for the sub strings, as "ed", "had", "Done", etc., This paper gives us an idea on working with API's to translate the input speech to the required output speech and thus increasing the efficiency of Speech Translation in cellular devices and also a mobile application that will help us to monitor all the audios present in mobile device and translate it into required language.