Music Annotation and Retrieval System Using Anti-Models

Chen ZS, Zen JM, Jang JSR. Music Annotation and Retrieval System Using Anti-Models. In: AES Convention 125. Audio Engineering Society; 2008. Paper 7540. Available from: https://aes.org/publications/elibrary-page/?id=14692

@inproceedings{Chen2008_14692,
  author = {Chen, Zhi-Sheng and Zen, Jia-Min and Jang, Jyh-Shing Roger},
  title = {{Music Annotation and Retrieval System Using Anti-Models}},
  booktitle = {AES Convention 125},
  note = {Paper 7540},
  year = {2008},
  month = oct,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=14692}
}

TY  - CPAPER
TI  - Music Annotation and Retrieval System Using Anti-Models
AU  - Chen, Zhi-Sheng
AU  - Zen, Jia-Min
AU  - Jang, Jyh-Shing Roger
T2  - AES Convention 125
M1  - Paper 7540
PY  - 2008
DA  - 2008/10/06
UR  - https://aes.org/publications/elibrary-page/?id=14692
PB  - Audio Engineering Society
LA  - en
AB  - Query-by-semantic-description (QBSD) is a natural way for searching/annotating music in a large database. We propose such a system by considering anti-words for each annotation word based on the concept of supervised multi-class labeling (SML). Moreover, words that are highly correlated with the anti-semantic meaning of a word constitute its anti-word set. By modeling both a word and its anti-word set, our system can achieve +8.21% and +1.6% gains of average precision and recall against SML under the condition of an equal average number of annotation words, that is, 10. By incorporating anti-models, we also allow queries with anti-semantic words, which is not an option for previous systems.
ER  -