Skip to content
/ Deep-Audio-Embedding Public

Visualizing the structure of audio in 3D using deep convolutional autoencoders

23 stars 4 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

M-Lin-DM/Deep-Audio-Embedding

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
Majulah
Majulah
 
 
Embed_audio_data_callable.py
Embed_audio_data_callable.py
 
 
Evaluate-LSTM-on-test.py
Evaluate-LSTM-on-test.py
 
 
Forecast-in-latent-space-KNN.py
Forecast-in-latent-space-KNN.py
 
 
Forecast-in-latent-space-LSTM.py
Forecast-in-latent-space-LSTM.py
 
 
Forecast-in-latent-space-MLP.py
Forecast-in-latent-space-MLP.py
 
 
Majulah.wav
Majulah.wav
 
 
Numerical-solution-divergence-Plots.ipynb
Numerical-solution-divergence-Plots.ipynb
 
 
Numerical-solution-divergence.py
Numerical-solution-divergence.py
 
 
Play_embedding.py
Play_embedding.py
 
 
Plot-with-ZForecast.py
Plot-with-ZForecast.py
 
 
Plot_compare_embeddings.py
Plot_compare_embeddings.py
 
 
README.md
README.md
 
 
Save-dataset_2sec-window.py
Save-dataset_2sec-window.py
 
 
Save-dataset_half-sec-window.py
Save-dataset_half-sec-window.py
 
 
Train_model_2sec-window.py
Train_model_2sec-window.py
 
 
Train_model_half-sec-window.py
Train_model_half-sec-window.py
 
 
train-latent-space-LSTM.py
train-latent-space-LSTM.py
 
 
train-latent-space-MLP.py
train-latent-space-MLP.py
 
 

Repository files navigation

Deep-Audio-Embedding

Visualizing the structure of audio in 3D using deep convolutional autoencoders. The code ultimately transforms .wav audio files into a timeseries in 3 dimensions.

See my blog post for a detailed description of this project.

About

Visualizing the structure of audio in 3D using deep convolutional autoencoders

Resources

Readme
Activity

Stars

23 stars

Watchers

2 watching

Forks

4 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages