Abstract

Vibrato is one of the key acoustic feature of singing voice. This work investigates the measurement of vibrato by\nextracting it from natural cappella section of singing voice considering variety of singing styles and tones. The algorithm\nperforms detection, extraction and analysis of vibrato parameters; rate and extent. These vibrato parameters are explored for\nsinger identification and is validated on a database of 11 singers (5 female and 6 male singers) containing more than 50\ncappella segments from several songs of each singer derived from commercially available CD recordings. A maximum\naccuracy of 62% is achieved in identifying the singers. This indicates the significance of vibrato as an important\ncharacteristic of singing voice.