Cross-Version Singing Voice Detection in Classical Opera Recordings

In the field of Music Information Retrieval (MIR), the automated detection of the singing voice within a given music recording constitutes a challenging and important research problem. In this study, our goal is to find those segments within a classical opera recording, where one or several singers are active. As our main contributions, we first propose a novel audio feature that extends a state-of-theart feature set that has previously been applied to singing voice detection in popular music recordings. Second, we describe a simple bootstrapping procedure that helps to improve the results in the case that the test data is not reflected well by the training data. Third, we show that a crossversion approach can help to stabilize the results even further.