Here’s the link to my talk. I talked about the procedure of applying deep learning (or machine learning in general) for audio-related task. Abstract was like..
Is deep learning Alchemy? No! But it heavily relies on tips and tricks, a set of common wisdom that probably works for similar problems. In this talk, I’ll introduce what the audio/music research societies have discovered while playing with deep learning when it comes to audio classification and regression — how to prepare the audio data and preprocess them, how to design the networks (or choose which one to steal from), and what we can expect as a result.
Slide deck is shared on slideshare.net. Let me embed here too.
It was my first time attending this kind of conference, less academic and more software engineer-targeted one. Putting aside the difference you can easily expect, after the talk, they gave me some stats of my talk/session/the whole conference, which were..
Green votes: 96.2%
Yellow votes: 3.8%
Red votes: 0.0%
Track: Sequential Data: Natural Language, Time Series, and Sound
Attendees in total: 422
Green votes: 87.0%
Yellow votes: 12.7%
Red votes: 0.3%
Green votes:: 87.6%
Yellow votes: 11.8%
Red votes: 0.6%
Almost everyone involved was happy (high precision!) So.. enjoy! 🙂