Stereo Panning Features for Classifying Recording Production Style

Recording engineers, mixers and producers play important yet often overlooked roles in defining the sound of a particular record, artist or group. The placement of different sound sources in space using stereo panning information is an important component of the production process. Audio classification systems typically convert stereo signals to mono and to the best of our knowledge have not utilized information related to stereo panning. In this paper we propose a set of audio features that can be used to capture stereo information. These features are shown to provide statistically important information for non-trivial audio classification tasks and are compared with the traditional Mel-Frequency Cepstral Coefficients. The proposed features can be viewed as a first attempt to capture extra-musical information related to the production process through music information retrieval techniques.