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.

: Deep models designed for detecting audio manipulation (e.g., resampling) are often evaluated at 64 kbps to ensure they can still identify global time-frequency variations despite the lossy compression. Common Applications at 64 kbps End-to-end Stereo Audio Coding Using Deep Neural Networks 64 kbps

In the context of audio processing and deep learning, (kilobits per second) refers to a common low-bitrate threshold used to test the robustness of deep features —the high-dimensional data representations extracted by neural networks from raw audio signals. Impact on Deep Features : Modern Neural Audio Codecs attempt to learn

: 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. Impact on Deep Features : Even a 64

: At 64 kbps, most signal details are preserved compared to lower bitrates (like 16 or 32 kbps), but the compression efficiency is significantly lower.