Mulimani, M.Koolagudi, S.G.2020-03-302020-03-302019IEEE Region 10 Annual International Conference, Proceedings/TENCON, 2019, Vol.2018-October, , pp.1460-1464https://idr.nitk.ac.in/handle/123456789/7187This paper investigates a new feature extraction method to extract different features from the spectrogram of an audio signal for Acoustic Event Classification (AEC). A new set of features is formulated and extracted from local spectrogram regions named blocks. The average recognition performance of proposed spectrogram based features and Mel-frequency cepstral coefficients (MFCCs) with their deltas and accelerations on Support Vector Machines (SVM) is compared. In this work, different categories of acoustic events are considered from the Freiburg-106 dataset. Proposed features show significantly improved performance over conventional Mel-frequency cepstral coefficients (MFCCs) for Acoustic Event Classification. � 2018 IEEE.Book chapter