PH_Pooled Featrues Classification MIREX 2011 Submission

Abstract

1. Principal Mel-Spectrum Components (Feature)
2. Temporal Pooling Functions (Model)
3. Single Hidden Layer Neural Network, thus Multi-layer Perceptron (Classifier)

Audio Preprocessing

    Feature: PMSC (Principal Mel-Spectrum Components)

1. Original Data:  30s, 22.05KHz, mono, wav
2. Process Steps:
1. DFT (spectral domain)
   we compute DFTs over windows of 1024 samples on audio at 22.05 KHz (i.e. roughly 46ms) with a frame step of 512 samples.
2. Mel-Compression
   we run the spectral amplitudes through a set of 256 mel-scaled triangular filters to abtain a set of spectral energy bands.
3. Principal Component analysis whitening (PCA whitening)
   we compute the principal components of a random sub-sample of training set. In order to obtain features with unitary variance, we multiply(乘以) each component by the inverse square of its eigenvalue(特征值平方的倒数). ---- PCA whitening.

Model

    PFC (Pooled Features Classifier)

1. Pooling Operation
   the model applies a given set of pooling functions (how many?) to the PMSC features, and sends the pooled features to a classifier(MLP, with hidden layer of 2000 units, sigmoid activation, L2 weight decay and cross-entropy cost).
2. Classify
   each pooling window is considered as a training example for the classifier, and average the predictions of the classifier over all the windows of a given clip to obtain the final classification (what is the rule?).

Tasks

1. Classification (train/test task)
   the MLP outputs an affinity prediction for each class (pooling functions tread each pooling window as a training example).
2. Tagging
1. Affinity
   the affinity scores for a song is thus directly the output of the MLP.
2. Binary Classification
   choose the threshold that optimizes the F1-score on the validation set.

Tools

1. Theano: Theano is a numerical computation library for Python. In Theano, computations are expressed using a NumPy-like syntax and compiled to run efficiently on either CPU or GPU architectures.
   
   来源： <http://en.wikipedia.org/wiki/Theano_(software)>

    

来自为知笔记(Wiz)