Multiple fundamental frequency estimation using Gaussian smoothness

Antonio Pertusa, Jose M. Inesta
2008 Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing  
The goal of a polyphonic music transcription system is to extract a score from an audio signal. A multiple fundamental frequency estimator is the main piece of these systems, whereas tempo detection and key estimation complement them to correctly extract the score. In this work, in order to detect the fundamental frequencies that are present in a signal, a set of candidates are selected from the spectrum, and all their possible combinations are generated. The best combination is chosen in a
more » ... e by frame analysis by applying a set of rules, taking into account the harmonic amplitudes and the spectral smoothness measure described in this work. The system was evaluated and compared to other works, yielding competitive results and performance.
doi:10.1109/icassp.2008.4517557 dblp:conf/icassp/PertusaI08 fatcat:msf3btca6necnlsfgcc2z74dpi