Skip to content
/ music-noise-segmentation-on-a-spectrogram Public

MNSS (Music Noise Segmentation on a Spectrogram) is a deep-neural network based preprocessing technique that pre-filters unnecessary noise. MNSS is based on the convolutional neural networks and uses softmax value as a probability of noise existence.

11 stars 1 fork Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

tango4j/music-noise-segmentation-on-a-spectrogram

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
.idea
.idea
 
 
MNSS
MNSS
 
 
audio_sample
audio_sample
 
 
confusion_matrix
confusion_matrix
 
 
music_noise_data
music_noise_data
 
 
pickle_folder
pickle_folder
 
 
pr_matrix
pr_matrix
 
 
result_data
result_data
 
 
tmp
tmp
 
 
tts_speech
tts_speech
 
 
MNSS_function.py
MNSS_function.py
 
 
MNSS_function.pyc
MNSS_function.pyc
 
 
MNSS_function_bk.py
MNSS_function_bk.py
 
 
NN_wrapper.py
NN_wrapper.py
 
 
NN_wrapper.pyc
NN_wrapper.pyc
 
 
README.md
README.md
 
 
RQA_func_NM.py
RQA_func_NM.py
 
 
RQA_func_det2.py
RQA_func_det2.py
 
 
RQA_func_rs.py
RQA_func_rs.py
 
 
RQA_func_spg.py
RQA_func_spg.py
 
 
RUN_THIS.py
RUN_THIS.py
 
 
finish_alarm.py
finish_alarm.py
 
 
finish_alarm.pyc
finish_alarm.pyc
 
 
md02.py
md02.py
 
 
mix_noise.py
mix_noise.py
 
 
mr00.py
mr00.py
 
 
nmr_plot.py
nmr_plot.py
 
 
pic_draw.py
pic_draw.py
 
 
plot_RQA_func_rs.py
plot_RQA_func_rs.py
 
 
read_cm.py
read_cm.py
 
 
set_file_func.py
set_file_func.py
 
 
set_file_func.pyc
set_file_func.pyc
 
 
set_file_func_novalid.py
set_file_func_novalid.py
 
 
set_file_func_novalid.pyc
set_file_func_novalid.pyc
 
 
test_set.py
test_set.py
 
 
test_set.pyc
test_set.pyc
 
 
test_set_val.py
test_set_val.py
 
 
test_set_val.pyc
test_set_val.pyc
 
 
tts.py
tts.py
 
 
tts.pyc
tts.pyc
 
 
vis_func.py
vis_func.py
 
 
vis_func.pyc
vis_func.pyc
 
 
xp00_nm.py
xp00_nm.py
 
 
xp00_nmr.py
xp00_nmr.py
 
 
xp00_nms.py
xp00_nms.py
 
 
xp00_s2.py
xp00_s2.py
 
 
xp00_s2.pyc
xp00_s2.pyc
 
 

Repository files navigation

music-noise-segmentation-on-a-spectrogram

  • Goal : An effective way to classify and analyze audio signal with deep neural networks.

  • The whole project is based on the Keras(Theano)

  • Python dependencies : matplotlib, scipy, numpy, pylab, librosa, pickle, scikits, keras, skimage

  • Must downloads : The learned weight of neural networks; Save this file into "pickel_folder"

https://www.dropbox.com/s/ivp28e2x6gp8hfx/NNM_cla_ss_0__music_noise__j26_0000000000002_SR11kHz_goodmare.pickle?dl=0

  • This technique is investigated for the purpose of making a preprocessing system for music information retrieval (MIR) techniques.

Note : As you can see in the above picture, the proposed convolutional neural networks successfully segments a spectrogram as their identity. For detailed information, refer to my paper that is presented in LBD session in ISMIR 2015. http://ismir2015.uma.es/LBD/LBD27.pdf

Ask any question : inctrljinee at gmail.com

About

MNSS (Music Noise Segmentation on a Spectrogram) is a deep-neural network based preprocessing technique that pre-filters unnecessary noise. MNSS is based on the convolutional neural networks and uses softmax value as a probability of noise existence.

Resources

Readme
Activity

Stars

11 stars

Watchers

2 watching

Forks

1 fork
Report repository

Releases

No releases published

Packages

No packages published

Languages