Normfeat
Copyright 2014-2015 Anthony Larcher and Sylvain Meignier
frontend provides methods to process an audio signal in order to extract
useful parameters for speaker verification.
-
frontend.normfeat.cms(features, label=[])[source]
Performs cepstral mean subtraction
Parameters: |
- features – a feature stream of dimension dim x nframes
where dim is the dimension of the acoustic features and nframes the
number of frames in the stream
- label – a logical verctor
|
Returns: | a feature stream
|
-
frontend.normfeat.cmvn(features, label=[])[source]
Performs mean and variance normalization
Parameters: |
- features – a feature stream of dimension dim x nframes
where dim is the dimension of the acoustic features and nframes the
number of frames in the stream
- label – a logical verctor
|
Returns: | a sequence of features
|
-
frontend.normfeat.normalize_feature_stream(features, label=[], mode='cmvn', win='301', normVar=False, keepAllFeatures=False)[source]
Normalize features from a feature stream by using either
‘cms’, ‘cmvn’ or ‘stg’
Parameters: |
- features – a feature stream to normalize
- label – a logical vector True if the frame should be processed.
By default, all frames are considered True.
- mode – normalization to apply: ‘cms’, ‘cmvn’ or ‘stg’.
Default is ‘cmvn’.
- win – for ‘stg’ mode only, size of the sliding window.
Default is 301.
- normVar – for ‘cmvn’ mode only, if True normalize the variance.
Default is False.
- keepAllFeatures – boolean, if True, keep also non-processed features
|
Returns: | a sequence of features
|
-
frontend.normfeat.rasta_filt(x)[source]
Apply RASTA filtering to the input signal.
Parameters: | x – the input audio signal to filter.
cols of x = critical bands, rows of x = frame
same for y but after filtering
default filter is single pole at 0.94 |
-
frontend.normfeat.stg(features, label=[], win=301)[source]
Performs feature warping on a sliding window
Parameters: | features – a feature stream of dimension dim x nframes
where dim is the dimension of the acoustic features and nframes the
number of frames in the stream |
Returns: | a sequence of features |