How Efficient is MPEG-7 for General Sound Recognition?

Kim HG, Sikora T. How Efficient is MPEG-7 for General Sound Recognition? In: AES Conference: 25th International Conference: Metadata for Audio. Audio Engineering Society; 2004. Paper 5-2. Available from: https://aes.org/publications/elibrary-page/?id=12814

@inproceedings{Kim2004_12814,
  author = {Kim, Hyoung-Gook and Sikora, Thomas},
  title = {{How Efficient is MPEG-7 for General Sound Recognition?}},
  booktitle = {AES Conference: 25th International Conference: Metadata for Audio},
  note = {Paper 5-2},
  year = {2004},
  month = jun,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=12814}
}

TY  - CPAPER
TI  - How Efficient is MPEG-7 for General Sound Recognition?
AU  - Kim, Hyoung-Gook
AU  - Sikora, Thomas
T2  - AES Conference: 25th International Conference: Metadata for Audio
M1  - Paper 5-2
PY  - 2004
DA  - 2004/06/06
UR  - https://aes.org/publications/elibrary-page/?id=12814
PB  - Audio Engineering Society
LA  - en
AB  - Our challenge is to analyze/classify video sound track content for indexing purposes. To this end we compare the performance of MPEG-7 Audio Spectrum Projection (ASP) features based on several basis decomposition algorithms vs. Mel-scale Frequency Cepstrum Coefficients (MFCC). For basis decomposition in the feature extraction we evaluate three approaches: Principal Component Analysis (PCA), Independent Component Analysis (ICA), and Non-negative Matrix Factorization (NMF). Audio features are computed from these reduced vectors and are fed into a continuous hidden Markov model (CHMM) classifier. Our conclusion is that established MFCC features yield better performance compared to MPEG-7 ASP in the general sound recognition under practical constraints.
ER  -