Detecting applause in both audio recordings and real-time performances is relevant in such applications as music information retrieval and spatial audio coding. A combination of mel-frequency cepstral coefficients and low-level descriptors yielded the best classification performance in the experiments. Low-pass filtering of the feature time series leads to the concept of sigma features. Binary misclassification occurs more often when applause and nonapplause with similar amplitudes are simultaneously present.
(See document for exact affiliation information.)
https://aes2.org/publications/elibrary-page/?id=15926
(641KB)
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 Join the AES. If you need to check your member status, login to the Member Portal.
