Subjective and Spectrogram Analysis of Speech Synthesizer for Marathi TTS Using Concatenative Synthesis

Paper describe the TTS system using Concatenative synthesis techniques for Marathi language with unit selection speech databases and discuss the issues relevant to the development of a Marathi speech synthesizer using different choice of units: words, phonemes, syllables as a database. The most important qualities of a speech synthesis system are naturalness and intelligibility. We Synthesize the Marathi sentences from the text. Performed the subjective evaluations and spectrogram analysis of the synthesized speech. As per the result 81% of speech synthesized by the proposed method was preferred to that by the conventional method, 40 speech sample were synthesized out of the different kinds of data . Naturalness increases with highest value of data. Spectrogram analysis for different words of the sentences with syllables & phonemes as unit.