We describe an efficient system, which directly extracts features from compressed audio material. It consists of a time/frequency conversion method and a feature extraction algorithm. The conversion method provides the feature extraction algorithm with a suitable complex spectral representation directly from the compressed domain. It further allows to trade-off between computational complexity and conversion accuracy. Several operating points using different conversion accuracies were tested with an MPEG audio identification system in order to evaluate the identification confidence. Based on these results it is possible to reduce the computational complexity from O(N log N) to O(N) compared to the conventional approach (complete decoding followed by a frequency analysis).
Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!
This paper costs $33 for non-members and is free for AES members and E-Library subscribers.