By Fabien Gouyon, François Pachet, and Olivier Delerue.
Proceedings of the COST G-6 Conference on Digital Audio Effects (DAFx-00), Verona, Italy, 7–9 December 2000.
Read the paper (PDF) · Official DAFx copy (PDF) · Publication record
About the paper
Zero-crossing rate measures how often an audio waveform changes sign. The paper examines how this feature can help distinguish bass-drum-like and snare-like sounds in recordings of popular music, as part of a method for locating percussion events in a mix.
Abstract
We address the issue of automatically extracting rhythm descriptors from audio signals, to be eventually used in content-based musical applications such as in the context of MPEG7. Our aim is to approach the comprehension of auditory scenes in raw polyphonic audio signals without preliminary source separation. As a first step towards the automatic extraction of rhythmic structures out of signals taken from the popular music repertoire, we propose an approach for automatically extracting time indexes of occurrences of different percussive timbres in an audio signal. Within this framework, we found that a particular issue lies in the classification of percussive sounds. In this paper, we report on the method currently used to deal with this problem.
Related work
Automatic Extraction of Drum Tracks from Polyphonic Music Signals (2002) uses zero-crossing rate in a system that reconstructs a drum track from a mixed recording.