64 Kbps 🌟

: Modern Neural Audio Codecs attempt to learn optimal transformations in a "latent space" (deep features) that provide better sound quality at 64 kbps than traditional codecs like HE-AAC.

When audio is compressed to 64 kbps (using codecs like MP3 or AAC), information is discarded to save space. Research shows this affects deep learning models in the following ways: 64 kbps

: Even a 64 kbps MP3 compression can decrease the accuracy of a Deep Neural Network (DNN) by roughly 4.98% in sensitive tasks like acoustic classification. : Modern Neural Audio Codecs attempt to learn