Generating Sound with Neural Networks: Difference between revisions
Jump to navigation
Jump to search
mNo edit summary |
|||
| (6 intermediate revisions by the same user not shown) | |||
| Line 4: | Line 4: | ||
= Sound Generation with Neural Networks - INTRO = | = Sound Generation with Neural Networks - INTRO = | ||
Ey8IZQl_lKs | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="Ey8IZQl_lKs" /> | ||
= Sound Generation with Deep Learning | |||
pwV8K9wXY2E | = Sound Generation with Deep Learning - Approaches and Challenges = | ||
<evlplayer id="player1" w="480" h="360" service="youtube" defaultid="pwV8K9wXY2E" /> | |||
0:00 Intro | |||
0:33 Defining the sound generation task | |||
1:17 Classification of sound generation systems | |||
2:14 Types of generated sounds | |||
3:41 Sound representations | |||
4:07 Generation from raw audio | |||
7:40 Challenges of raw audio generation | |||
10:21 Generation from spectrograms | |||
16:12 Advantages of generation from spectrograms | |||
18:07 Challenges of generation from spectrograms | |||
20:26 Can we generate sound with MFCCs? | |||
21:26 DL architectures for sound generation | |||
22:13 Inputs for generation | |||
24:03 Details about the sound generative system we'll build | |||
24:44 What's next? | |||
Mentioned papers: | |||
* Wavenet: A Generative Model for Raw Audio: | |||
https://arxiv.org/pdf/1609.03499.pdf | |||
* Jukebox: A Generative Model for Music | |||
https://arxiv.org/pdf/2005.00341 | |||
* DrumGAN: Synthesis of Drum Sounds with Timbral Feature Conditioning Using Generative Adversarial Networks | |||
https://arxiv.org/pdf/2008.12073 | |||
* Melnet: A generative model for audio in the frequency domain | |||
https://arxiv.org/pdf/1906.01083.pdf | |||
= Autoencoders Explained Easily= | = Autoencoders Explained Easily= | ||
xwrzh4e8DLs | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="xwrzh4e8DLs" /> | ||
= How to Implement Autoencoders in Python and Keras | = How to Implement Autoencoders in Python and Keras || The Encoder = | ||
TtyoFTyJuEY | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="TtyoFTyJuEY" /> | ||
= How to Implement Autoencoders in Python and Keras - The Decoder = | = How to Implement Autoencoders in Python and Keras - The Decoder = | ||
SF1uAtU5-BU | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="SF1uAtU5-BU" /> | ||
= Building and Training an Autoencoder in Keras + TensorFlow + Python = | = Building and Training an Autoencoder in Keras + TensorFlow + Python = | ||
6fZdJKm-fSk | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="6fZdJKm-fSk" /> | ||
= Saving the Autoencoder in Keras = | = Saving the Autoencoder in Keras = | ||
UIC0Irq-Eok | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="UIC0Irq-Eok" /> | ||
= Generation with AutoEncoders: Results and Limitations = | = Generation with AutoEncoders: Results and Limitations = | ||
-HqG2s4dxJ0 | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="-HqG2s4dxJ0" /> | ||
= From Autoencoders to Variational Autoencoders: Improving the Encoder = | = From Autoencoders to Variational Autoencoders: Improving the Encoder = | ||
b8AzCgY1gZI | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="b8AzCgY1gZI" /> | ||
= From Autoencoders to Variational Autoencoders: Improving the Loss Function = | = From Autoencoders to Variational Autoencoders: Improving the Loss Function = | ||
lRsqFbgGyKg | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="lRsqFbgGyKg" /> | ||
= How to implement a Variational AutoEncoder in Python and Keras = | = How to implement a Variational AutoEncoder in Python and Keras = | ||
A6mdOEPGM1E | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="A6mdOEPGM1E" /> | ||
= Preprocessing Audio Datasets for Machine Learning = | = Preprocessing Audio Datasets for Machine Learning = | ||
O04v3cgHNeM | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="O04v3cgHNeM" /> | ||
= Training a VAE with Speech Data in Keras = | = Training a VAE with Speech Data in Keras = | ||
UGTAzMX3vjQ | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="UGTAzMX3vjQ" /> | ||
= Generating Sound Digits with a Variational AutoEncoder = | = Generating Sound Digits with a Variational AutoEncoder = | ||
fWSoEqWNh8w | <evlplayer id="player1" w="480" h="360" service="youtube" defaultid="fWSoEqWNh8w" /> | ||
Latest revision as of 16:37, 12 December 2021
Generating Sound with Neural Networks
Learn how to generate sound from audio files 🎧 🎧 using Variational Autoencoders.
Sound Generation with Neural Networks - INTRO[edit]
Sound Generation with Deep Learning - Approaches and Challenges[edit]
0:00 Intro 0:33 Defining the sound generation task 1:17 Classification of sound generation systems 2:14 Types of generated sounds 3:41 Sound representations 4:07 Generation from raw audio 7:40 Challenges of raw audio generation 10:21 Generation from spectrograms 16:12 Advantages of generation from spectrograms 18:07 Challenges of generation from spectrograms 20:26 Can we generate sound with MFCCs? 21:26 DL architectures for sound generation 22:13 Inputs for generation 24:03 Details about the sound generative system we'll build 24:44 What's next?
Mentioned papers:
- Wavenet: A Generative Model for Raw Audio:
https://arxiv.org/pdf/1609.03499.pdf
- Jukebox: A Generative Model for Music
https://arxiv.org/pdf/2005.00341
- DrumGAN: Synthesis of Drum Sounds with Timbral Feature Conditioning Using Generative Adversarial Networks
https://arxiv.org/pdf/2008.12073
- Melnet: A generative model for audio in the frequency domain
https://arxiv.org/pdf/1906.01083.pdf
Autoencoders Explained Easily[edit]
How to Implement Autoencoders in Python and Keras || The Encoder[edit]
How to Implement Autoencoders in Python and Keras - The Decoder[edit]
Building and Training an Autoencoder in Keras + TensorFlow + Python[edit]
Saving the Autoencoder in Keras[edit]
Generation with AutoEncoders: Results and Limitations[edit]
From Autoencoders to Variational Autoencoders: Improving the Encoder[edit]
From Autoencoders to Variational Autoencoders: Improving the Loss Function[edit]
How to implement a Variational AutoEncoder in Python and Keras[edit]
Preprocessing Audio Datasets for Machine Learning[edit]
Training a VAE with Speech Data in Keras[edit]