A Joint Approach to Extract Multiple Fundamental Frequency in Polyphonic Signals Minimizing Gaussian Spectral Distance

Cañadas-Quesada FJ, Vera-Candeas P, Ruiz-Reyes N, Carabias-Orti JJ, Martínez Munoz D. A Joint Approach to Extract Multiple Fundamental Frequency in Polyphonic Signals Minimizing Gaussian Spectral Distance. In: AES Convention 126. Audio Engineering Society; 2009. Paper 7756. Available from: https://aes.org/publications/elibrary-page/?id=14952

@inproceedings{CanadasQuesada2009_14952,
  author = {Cañadas-Quesada, Francisco J. and Vera-Candeas, Pedro and Ruiz-Reyes, Nicolás and Carabias-Orti, Julio J. and Martínez Munoz, Damián},
  title = {{A Joint Approach to Extract Multiple Fundamental Frequency in Polyphonic Signals Minimizing Gaussian Spectral Distance}},
  booktitle = {AES Convention 126},
  note = {Paper 7756},
  year = {2009},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14952}
}

TY  - CPAPER
TI  - A Joint Approach to Extract Multiple Fundamental Frequency in Polyphonic Signals Minimizing Gaussian Spectral Distance
AU  - Cañadas-Quesada, Francisco J.
AU  - Vera-Candeas, Pedro
AU  - Ruiz-Reyes, Nicolás
AU  - Carabias-Orti, Julio J.
AU  - Martínez Munoz, Damián
T2  - AES Convention 126
M1  - Paper 7756
PY  - 2009
DA  - 2009/05/06
UR  - https://aes.org/publications/elibrary-page/?id=14952
PB  - Audio Engineering Society
LA  - en
AB  - This paper presents a joint estimation approach to extract multiple fundamental frequency (F0) in monaural polyphonic music signals. In a frame-based analysis, we generate a spectral envelope for each combination of F0 candidates, from non-overlapped partials, under assumption that a harmonic sound is characterized by a Gaussian mixture model (GMM). The optimal F0 candidates combination minimizes a spectral Euclidean distance measure between the original spectrum and Gaussian spectral models. Evaluation was carried out using several piano recordings. Evaluation show promising results.
ER  -