Singing voice identification using harmonic spectral envelope

The paper presents a novel approach to identify the singers using harmonic spectral envelope constructed from pitch of singing voice. This new representation of singing voice demonstrates that harmonic spectral envelope exhibits certain acoustic qualities that can characterize the identity of the singer. Two different approaches are implemented to extract the pitch of singing voice; Cepstrum technique and Linear Predictive coding. Ten singers comprising of six male and four female singers are analyzed in this work. To have accurate analysis and estimation of acoustics of singing voice only cappella sections are investigated. Along with discussion on singer identification, the results include comparison of pitch extraction techniques and gender identification of singer. We achieve an average accuracy of 77% in identifying the singers, covering a large class of polyphonic recordings of Indian movie songs.