TUT ACOUSTIC SCENE CLASSIFICATION SUBMISSION

This technical report presents the details of our submission to the D-CASE classification challenge, Task 1: Acoustic Scene Classification. The method used consists in a feature extraction phase followed by two dimensionality reduction steps (PCA and LDA) the classification being done using the k nearest-neighbours algorithm.

[1]  Haihua Xu,et al.  A hybrid visual feature extraction method for audio-visual speech recognition , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[2]  Kun-Ming Yu,et al.  Automatic Music Genre Classification Based on Modulation Spectral Analysis of Spectral and Cepstral Features , 2009, IEEE Transactions on Multimedia.

[3]  Benjamin Schrauwen,et al.  Multiscale Approaches To Music Audio Feature Learning , 2013, ISMIR.

[4]  Justin Salamon,et al.  Unsupervised feature learning for urban sound classification , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[5]  Tuomas Virtanen,et al.  TUT database for acoustic scene classification and sound event detection , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).