Text to speech system for Kannada language

The recent advancements in the speech processing domain are speech recognition , speech synthesis, speech analysis and coding. Speech synthesis is the artificial production of human speech. A computer system used for the purpose is called a speech synthesizer and can be implemented in software or hardware products. A text-to-speech (TTS) system converts normal language text into speech; The paper presents the development of text to speech system for one of the south Indian languages, Kannada, the official language of Karnataka. The paper presents the segmentation of Kannada text into the smallest units of the word and concatenating sound pieces extracted from recorded speech that are stored in database to produce speech output. Hence the proposed work uses concatenation method of speech synthesis on MATLAB 2010 platform to achieve high degree of accuracy which is judged by its similarity to the human voice and by its ability to be understood clearly. TTS applications are well known as assistive aides for people who experience dyslexia, reading challenges, or visual impairment. The other valuable uses for the application range from reducing eye strain from reading (digital or paper formats), reducing paper use due to printing digital text, foreign language learning, writing and editing, or promoting listening skills.