Singing Voice Synthesis System for Carnatic Music

Singing Voice Synthesis systems take speech, lyric and note information as inputs, and produce songs as the output. For converting speech to song, the duration and pitch of the speech need to be modified to match the desired pitch and duration of the song. In this paper, we propose a baseline speech to singing voice synthesis system for Carnatic music. We synthesize two popular Carnatic songs from the flat pitched recordings of a vowel sound. Pitch of the input sound is modified according to the frequencies of notes present in the original songs. To avoid abrupt pitch changes, transitions between adjacent notes are smoothed using a sinusoid-based function. To add naturalness to the synthesized song, fluctuations present in input speech are retained. Harmonic plus Noise Model is used to synthesize the songs. Subjective evaluation is performed by ten listeners, and the Mean Opinion Scores for the songs are found to be 3.1 and 3.