Nearest-neighbor Generic Sound Classification with a WordNet-based Taxonomy

Cano P, Koppenberger M, Herrera P, Le Groux S, Ricard J, Wack N. Nearest-neighbor Generic Sound Classification with a WordNet-based Taxonomy. In: AES Convention 116. Audio Engineering Society; 2004. Paper 6139. Available from: https://aes.org/publications/elibrary-page/?id=12784

@inproceedings{Cano2004_12784,
  author = {Cano, Pedro and Koppenberger, Markus and Herrera, Perfecto and Le Groux, Sylvain and Ricard, Julien and Wack, Nicolas},
  title = {{Nearest-neighbor Generic Sound Classification with a WordNet-based Taxonomy}},
  booktitle = {AES Convention 116},
  note = {Paper 6139},
  year = {2004},
  month = may,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=12784}
}

TY  - CPAPER
TI  - Nearest-neighbor Generic Sound Classification with a WordNet-based Taxonomy
AU  - Cano, Pedro
AU  - Koppenberger, Markus
AU  - Herrera, Perfecto
AU  - Le Groux, Sylvain
AU  - Ricard, Julien
AU  - Wack, Nicolas
T2  - AES Convention 116
M1  - Paper 6139
PY  - 2004
DA  - 2004/05/06
UR  - https://aes.org/publications/elibrary-page/?id=12784
PB  - Audio Engineering Society
LA  - en
AB  - Audio classification methods work well when fine-tuned to reduced domains, such as musical instrument classification or simplified sound effects taxonomies. Classification methods cannot currently offer the detail needed in general sound recognition. A real-world-sound recognition tool would require thousands of classifiers, each specialized in distinguishing little details and a taxonomy that represents the real world. We describe the use of WordNet, a semantic network that organizes real world knowledge as the taxonomy backbone. In order to overcome the huge number of classifiers to distinguish an ever growing number of sounds, the recognition engine uses nearest-neighbor classifier with a database of isolated sounds unambiguously linked to WordNet concepts.
ER  -