Brand new to RX 6 is Dialogue Isolate, which uses a deep neural network, trained on large amounts of speech and noise data, to automatically recognize and separate spoken dialogue from non-stationary background noise, such as crowds, footsteps, weather, or other noise with highly variable characteristics, meaning we can take a noisy dialogue track, like this…

[dialogue track]

And make it sound like this.

[dialogue track, after processing]

For more information, and to download your own test files to use in RX 6, head to izotope.com/RX.