Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

Commit 726cb75

Browse filesBrowse files
author
ybdarrenwang
committed
recover README
1 parent 11d2163 commit 726cb75
Copy full SHA for 726cb75

1 file changed

+42-42Lines changed: 42 additions & 42 deletions

File tree

Expand file treeCollapse file tree
Open diff view settings
Filter options
Expand file treeCollapse file tree
Open diff view settings
Collapse file

‎README.rst‎

Copy file name to clipboardExpand all lines: README.rst
+42-42Lines changed: 42 additions & 42 deletions
  • Display the source diff
  • Display the rich diff
Original file line numberDiff line numberDiff line change
@@ -15,13 +15,13 @@ This `project is on pypi <https://pypi.python.org/pypi/python_speech_features>`_
1515

1616
To install from pypi::
1717

18-
pip install python_speech_features
18+
pip install python_speech_features
1919

20-
20+
2121
From this repository::
2222

23-
git clone https://github.com/jameslyons/python_speech_features
24-
python setup.py develop
23+
git clone https://github.com/jameslyons/python_speech_features
24+
python setup.py develop
2525

2626

2727
Usage
@@ -45,28 +45,28 @@ MFCC Features
4545
The default parameters should work fairly well for most cases,
4646
if you want to change the MFCC parameters, the following parameters are supported::
4747

48-
python
49-
def mfcc(signal,samplerate=16000,winlen=0.025,winstep=0.01,numcep=13,
50-
nfilt=26,nfft=512,lowfreq=0,highfreq=None,preemph=0.97,
48+
python
49+
def mfcc(signal,samplerate=16000,winlen=0.025,winstep=0.01,numcep=13,
50+
nfilt=26,nfft=512,lowfreq=0,highfreq=None,preemph=0.97,
5151
ceplifter=22,appendEnergy=True)
5252

53-
============= ===========
54-
Parameter Description
55-
============= ===========
56-
signal the audio signal from which to compute features. Should be an N*1 array
57-
samplerate the samplerate of the signal we are working with.
58-
winlen the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)
59-
winstep the step between successive windows in seconds. Default is 0.01s (10 milliseconds)
60-
numcep the number of cepstrum to return, default 13
61-
nfilt the number of filters in the filterbank, default 26.
62-
nfft the FFT size. Default is 512
63-
lowfreq lowest band edge of mel filters. In Hz, default is 0
64-
highfreq highest band edge of mel filters. In Hz, default is samplerate/2
65-
preemph apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97
66-
ceplifter apply a lifter to final cepstral coefficients. 0 is no lifter. Default is 22
67-
appendEnergy if this is true, the zeroth cepstral coefficient is replaced with the log of the total frame energy.
68-
returns A numpy array of size (NUMFRAMES by numcep) containing features. Each row holds 1 feature vector.
69-
============= ===========
53+
============= ===========
54+
Parameter Description
55+
============= ===========
56+
signal the audio signal from which to compute features. Should be an N*1 array
57+
samplerate the samplerate of the signal we are working with.
58+
winlen the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)
59+
winstep the step between successive windows in seconds. Default is 0.01s (10 milliseconds)
60+
numcep the number of cepstrum to return, default 13
61+
nfilt the number of filters in the filterbank, default 26.
62+
nfft the FFT size. Default is 512
63+
lowfreq lowest band edge of mel filters. In Hz, default is 0
64+
highfreq highest band edge of mel filters. In Hz, default is samplerate/2
65+
preemph apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97
66+
ceplifter apply a lifter to final cepstral coefficients. 0 is no lifter. Default is 22
67+
appendEnergy if this is true, the zeroth cepstral coefficient is replaced with the log of the total frame energy.
68+
returns A numpy array of size (NUMFRAMES by numcep) containing features. Each row holds 1 feature vector.
69+
============= ===========
7070

7171

7272
Filterbank Features
@@ -77,29 +77,29 @@ For most applications you will want the logarithm of these features.
7777
The default parameters should work fairly well for most cases.
7878
If you want to change the fbank parameters, the following parameters are supported::
7979

80-
python
81-
def fbank(signal,samplerate=16000,winlen=0.025,winstep=0.01,
80+
python
81+
def fbank(signal,samplerate=16000,winlen=0.025,winstep=0.01,
8282
nfilt=26,nfft=512,lowfreq=0,highfreq=None,preemph=0.97)
8383

84-
============= ===========
85-
Parameter Description
86-
============= ===========
87-
signal the audio signal from which to compute features. Should be an N*1 array
88-
samplerate the samplerate of the signal we are working with
89-
winlen the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)
90-
winstep the step between seccessive windows in seconds. Default is 0.01s (10 milliseconds)
91-
nfilt the number of filters in the filterbank, default 26.
92-
nfft the FFT size. Default is 512.
93-
lowfreq lowest band edge of mel filters. In Hz, default is 0
94-
highfreq highest band edge of mel filters. In Hz, default is samplerate/2
95-
preemph apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97
96-
returns A numpy array of size (NUMFRAMES by nfilt) containing features. Each row holds 1 feature vector. The second return value is the energy in each frame (total energy, unwindowed)
97-
============= ===========
84+
============= ===========
85+
Parameter Description
86+
============= ===========
87+
signal the audio signal from which to compute features. Should be an N*1 array
88+
samplerate the samplerate of the signal we are working with
89+
winlen the length of the analysis window in seconds. Default is 0.025s (25 milliseconds)
90+
winstep the step between seccessive windows in seconds. Default is 0.01s (10 milliseconds)
91+
nfilt the number of filters in the filterbank, default 26.
92+
nfft the FFT size. Default is 512.
93+
lowfreq lowest band edge of mel filters. In Hz, default is 0
94+
highfreq highest band edge of mel filters. In Hz, default is samplerate/2
95+
preemph apply preemphasis filter with preemph as coefficient. 0 is no filter. Default is 0.97
96+
returns A numpy array of size (NUMFRAMES by nfilt) containing features. Each row holds 1 feature vector. The second return value is the energy in each frame (total energy, unwindowed)
97+
============= ===========
9898

9999

100100
Reference
101101
=========
102102
sample english.wav obtained from::
103103

104-
wget http://voyager.jpl.nasa.gov/spacecraft/audio/english.au
105-
sox english.au -e signed-integer english.wav
104+
wget http://voyager.jpl.nasa.gov/spacecraft/audio/english.au
105+
sox english.au -e signed-integer english.wav

0 commit comments

Comments
0 (0)
Morty Proxy This is a proxified and sanitized view of the page, visit original site.