AudioGen: Textually Guided Audio Generation | Text To Audio | Paper Explained

Описание: ❤️ Become The AI Epiphany Patreon ❤️
  / theaiepiphany  

👨‍👩‍👧‍👦 Join our Discord community 👨‍👩‍👧‍👦
  / discord  

In this video I do a deep dive of the recent "AudioGen: Textually Guided Audio Generation | Paper Explained" paper that introduced text-guided audio synthesis.

In a nutshell, it's the VQ-VAE/GAN idea applied to the audio modality.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
✅ Paper: https://felixkreuk.github.io/text2aud...
✅ Site: https://felixkreuk.github.io/text2aud...

✅ 3B1B on Fourier transform:    • But what is the Fourier Transform?  A visu...  
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

⌚️ Timetable:
00:00 Intro
01:17 Why is text-to-audio hard?
02:51 Comparison with VQ-GAN
05:15 Comparison with SoundStream
06:20 AudioGen overview
09:10 Deep dive: audio representation, LSTM
14:05 Losses explained
17:40 Complex-valued STFTs
21:57 Audio Language Modeling
23:37 Multi-stream audio inputs
25:32 Data and augmentations
29:05 Results
35:28 Outro

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
💰 BECOME A PATREON OF THE AI EPIPHANY ❤️

If these videos, GitHub projects, and blogs help you,
consider helping me out by supporting me on Patreon!

The AI Epiphany -   / theaiepiphany  
One-time donation - https://www.paypal.com/paypalme/theai...

Huge thank you to these AI Epiphany patreons:
Eli Mahler
Petar Veličković

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

💼 LinkedIn -   / aleksagordic  
🐦 Twitter -   / gordic_aleksa  
👨‍👩‍👧‍👦 Discord -   / discord  

📺 YouTube -    / theaiepiphany  
📚 Medium -   / gordicaleksa  
💻 GitHub - https://github.com/gordicaleksa
📢 AI Newsletter - https://aiepiphany.substack.com/

▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

#audiogen #audiosynthesis #multimodal