How AI boosted audio processing?
summary
Covers the progression of neural-network approaches for audio denoising: WaveNet (2016) demonstrated high-quality noise reduction but was too computationally heavy for real-time on typical PCs; U-Net (2017) adapted from image processing improved quality but still couldn’t run real-time on laptops; and from 2019 convolutional neural networks enabled practical, real-time AI-based noise reduction. Explains how these NN architectures are applied to enhance speech and voice signals.
AI-written summary · about
related talks
21mCan AI Disrupt Speech Compression?
44mNeural Networks in Sound Analysis and Generation
28mHow to use Deep Learning to process audio data and classify sounds.
39mML Denoising With Tensor Flow
45mAuditory Intelligence : beyond speech recognition
27mThe Story of End to End Models in Deep Learning
21mDeveloping Machine Learning Based Speech Enhancement Models for Teams and Skype
11mAutomation of AI: Accelerating the AI Revolution