Estimating Instrument Spectral Envelopes for Polyphonic Music Transcription in a Music Scene-Adaptive Approach

Carabias-Orti JJ, Vera-Candeas P, Ruiz-Reyes N, Cañadas-Quesada FJ, Cabañas-Molero P. Estimating Instrument Spectral Envelopes for Polyphonic Music Transcription in a Music Scene-Adaptive Approach. In: AES Convention 126. Audio Engineering Society; 2009. Paper 7819. Available from: https://aes.org/publications/elibrary-page/?id=15015

@inproceedings{CarabiasOrti2009_15015,
  author = {Carabias-Orti, Julio J. and Vera-Candeas, Pedro and Ruiz-Reyes, Nicolás and Cañadas-Quesada, Francisco J. and Cabañas-Molero, Pablo},
  title = {{Estimating Instrument Spectral Envelopes for Polyphonic Music Transcription in a Music Scene-Adaptive Approach}},
  booktitle = {AES Convention 126},
  note = {Paper 7819},
  year = {2009},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=15015}
}

TY  - CPAPER
TI  - Estimating Instrument Spectral Envelopes for Polyphonic Music Transcription in a Music Scene-Adaptive Approach
AU  - Carabias-Orti, Julio J.
AU  - Vera-Candeas, Pedro
AU  - Ruiz-Reyes, Nicolás
AU  - Cañadas-Quesada, Francisco J.
AU  - Cabañas-Molero, Pablo
T2  - AES Convention 126
M1  - Paper 7819
PY  - 2009
DA  - 2009/05/06
UR  - https://aes.org/publications/elibrary-page/?id=15015
PB  - Audio Engineering Society
LA  - en
AB  - We propose a method for estimating the spectral envelope pattern of musical instruments in an musical scene-adaptive scheme, without having any prior knowledge about the real transcription. A musical note is defined as stable when variations between its harmonic amplitudes are held constant during a certain period of time. A density-based clustering algorithm is used with the stable notes in order to separate different envelope models for each note. Music scene-adaptive envelope patterns are finally obtained from similarity and continuity of the different note models. Our approach has been tested in a polyphonic music transcription scheme with synthesized and real music recordings, obtaining very promising results.
ER  -