KHiTE: Multilingual Speech Acquisition to Monolingual Text Translation

Objectives: To develop a system that accepts cross-lingual spoken reviews consisting of two to four languages, translate target language text for Indic languages namely Kannada, Hindi, Telugu and/or English termed as cross lingual speech identification and translation system. Methods: Hybridization software engineering models are used in natural pre-processing such noise removal splitting obtain phonemes. Combinatorial Hidden-Markov-Model, Artificial Neural Networks, Deep Networks Convulutional were deployed direct indirect mapping. Trained corpus thousand phonemes the form wave files each considered is named KHiTEShabdanjali. The basic parameters cosidered training dataset pause, pitch, sampling frequency, threshold etc. Findings: research has resulted development mono-lingual multi-lingual identification, tool processing mono-lingual, bi-lingual, tri-lingual quad-lingual monolingual languages. It generic approach can be other regional India by with selected language. Novelty: Cross-lingual helps users e-shopping reducing time incurred making decision purchase product having enough features at an economical price, e-tutoring, e-farming activities, digitizing, defence Keywords: Networks; HiddenMarkovModel; Speech Processing