On the Usefulness of Differentiated Transient/Steady-state Processing in Machine Recognition of Musical Instruments

Daudet L, David B, EssidSSID S, Leveau P, Richard G. On the Usefulness of Differentiated Transient/Steady-state Processing in Machine Recognition of Musical Instruments. In: AES Convention 118. Audio Engineering Society; 2005. Paper 6415. Available from: https://aes.org/publications/elibrary-page/?id=13131

@inproceedings{Daudet2005_13131,
  author = {Daudet, Laurent and David, Bertrand and EssidSSID, Slim and Leveau, Pierre and Richard, Gael},
  title = {{On the Usefulness of Differentiated Transient/Steady-state Processing in Machine Recognition of Musical Instruments}},
  booktitle = {AES Convention 118},
  note = {Paper 6415},
  year = {2005},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=13131}
}

TY  - CPAPER
TI  - On the Usefulness of Differentiated Transient/Steady-state Processing in Machine Recognition of Musical Instruments
AU  - Daudet, Laurent
AU  - David, Bertrand
AU  - EssidSSID, Slim
AU  - Leveau, Pierre
AU  - Richard, Gael
T2  - AES Convention 118
M1  - Paper 6415
PY  - 2005
DA  - 2005/05/06
UR  - https://aes.org/publications/elibrary-page/?id=13131
PB  - Audio Engineering Society
LA  - en
AB  - This paper addresses the usefulness of the segmentation of musical sounds into transient/non-transient parts for the task of machine recognition of musical instruments. We put into light the discriminative power of the attack-transient segments on the basis of objective criteria, consistent with the well-known psychoacoustics findings. Moreover, we show that, paradoxically, it is not always optimal to consider such a segmentation of the audio in a machine recognition system given decision length constraints. Our evaluation exploits efficient automatic segmentation techniques, a wide variety of signal processing features as well as feature selection algorithms and Support Vector Machine classification. The sound database used is composed of real-world mono-instrument phrases.
ER  -