Skip to content
Branch: master
Find file Copy path
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
54 lines (41 sloc) 1.68 KB
# Summary: Generates Clustering Features
# This analysis outputs:
# 1. an image of the clusters' centroids
# 2. a csv file that contains the vectors of the clusters' centroids
# 3. a csv file that contains clusters' id and size
# 4. a csv file that contains feature vectors
# The feature vectors can be used in training the machine learning models.
# The directory for the output of parallel job running on MahnooshSandpit
# OutputDirectory: "D:\Mahnoosh\Liz\ParallelJobs\"
# The properties to generate Mel scale
FrequencyScaleType: Mel
# HertzInterval: 1000
FrameSize: 1024
FinalBinCount: 128
# The default values for minFreqBin and maxFreqBin are 1 and FinalBinCount
# For any other arbitrary frequency bin bounds, these two parameters need to be manually set.
MinFreqBin: 24
MaxFreqBin: 82
# The number of frequency band for feature generation process
numFreqBand: 1
# The width and height of the patches to be taken from the patch sampling set
# A default patch is a single full-band frame which patchWidth = (maxFreqBin - minFreqBin + 1) / numFreqBand, patchHeight = 1
# PatchWidth: 5
PatchHeight: 1
# the number of frames that their feature vectors will be concatenated in order to preserve temporal information.
FrameWindowLength : 1
# the step size to make a window of frames
StepSize : 1
# The number of patches to be selected from each recording of the patch sampling set
NumRandomPatches: 1000
# the number of clusters to be generated from the selected patch set
NumClusters: 256
# Applying noise reduction and whitening if these options are set to 'true'
DoNoiseReduction: true
DoWhitening: true
# The factor of data downsampling using max pooling
MaxPoolingFactor: 6
You can’t perform that action at this time.