Deep Neural Networks with Music Dereverberation for Technical Ear Training in Music Production Education

Reverberation is an audio effect used in music production affecting the audio spectrum, as well as the timbre, of music. Technical ear training concerning the ways that reverberation works on music samples is important, since in order to achieve the desired texture sound engineers need to be able to perceive subtle audio changes. However, “dry” recordings, i.e. those that lack reverberation, are not universally available for music production students for the purposes of practice. In this paper, we propose a deep learning-based music dereverberation method to generate de-reverbed music samples for technical ear training in music production education. The experiment results show that based on various objective evaluation metrics, the proposed method can effectively realize dereverberation compared to other neural network-based methods.