Popular singer identification based on cepstrum transformation

A prerequisite for identifying the singers in popular music recordings is to reduce the interference of background accompaniment when trying to characterize the singer voice. This study proposes a background music removal approach for singer identification (SID) by exploiting the underlying relationships between solo voices and their accompanied versions in cepstrum. The relationships are characterized by a transformation estimated using a large set of accompanied singing generated by manually mixing solo singing with the accompaniments extracted from Karaoke VCD. This transformation reflects the cepstrum variations of a singing voice before and after it is added with accompaniments. When an unknown accompanied voice is to be identified by our system, we convert its cepstrum into a solo-like one based on the pre-trained transformation. Our experiments show that such a background music removal approach improves the SID accuracy noticeably.