Synthetic Voice Harmonization: A Fast and Precise Method

Abstract

Musicians often lack the ability to harmonize their voices within a track. To help with this matter, a tool can be developed for detecting the scale or key in which a track is sung and synthesizing pitches to make a triadchord or a tetrachord (combinations of three or four notes that fit in the scale's harmony) for each corresponding tone in the melody. In this paper, we present a fast and precise method to detect the pitch of voice and shift it to the appropriate frequencies, consequently building up a harmony out of the original melody. Four techniques are involved in this sequential process: segmentation into consonant and vowel intervals, pitch detection by the McLeod Pitch Method (MPM), functional harmony for establishing a cadence, and pitch shifting by means of a phase vocoder.