Training-Based Semantic Descriptors Modeling for Violin Quality Sound Characterization

Zanoni M, Setragno F, Antonacci F, Sarti A, Fazekas G, Sandler MB. Training-Based Semantic Descriptors Modeling for Violin Quality Sound Characterization. In: AES Convention 138. Audio Engineering Society; 2015. Paper 9353. Available from: https://aes.org/publications/elibrary-page/?id=17777

@inproceedings{Zanoni2015_17777,
  author = {Zanoni, Massimiliano and Setragno, Francesco and Antonacci, Fabio and Sarti, Augusto and Fazekas, György and Sandler, Mark B.},
  title = {{Training-Based Semantic Descriptors Modeling for Violin Quality Sound Characterization}},
  booktitle = {AES Convention 138},
  note = {Paper 9353},
  year = {2015},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=17777}
}

TY  - CPAPER
TI  - Training-Based Semantic Descriptors Modeling for Violin Quality Sound Characterization
AU  - Zanoni, Massimiliano
AU  - Setragno, Francesco
AU  - Antonacci, Fabio
AU  - Sarti, Augusto
AU  - Fazekas, György
AU  - Sandler, Mark B.
T2  - AES Convention 138
M1  - Paper 9353
PY  - 2015
DA  - 2015/05/06
UR  - https://aes.org/publications/elibrary-page/?id=17777
PB  - Audio Engineering Society
LA  - en
AB  - Violin makers and musicians describe the timbral qualities of violins using semantic terms coming from natural language. In this study we use regression techniques of machine intelligence and audio features to model in a training-based fashion a set of high-level (semantic) descriptors for the automatic annotation of musical instruments. The most relevant semantic descriptors are collected through interviews to violin makers. These descriptors are then correlated with objective features extracted from a set of violins from the historical and contemporary collections of the Museo del Violino and of the International School of Luthiery both in Cremona. As sound description can vary throughout a performance, our approach also enables the modeling of time-varying (evolutive) semantic annotations.
ER  -