What is the AI Enhancement actually doing?

What is the AI Enhancement actually doing to my dialogue recording? And which preset is best suited for me?

There are three enhancement presets in our Nomono Cloud:

  • Full Enhancement is for you who want your audio to be fully processed with one click. Quick, simple and great audio quality.
  • Medium Enhancement is for you who want to let our AI Enhancement do most of the processing, but still want to so some final tweaks within your own editing software.
  • Light Enhancement is for you who just want to remove the worst noise and bleed, before you continue to do all sound design and processing, within your own editing software.

Here's some information about which processes is included in each Enhancement preset:

  Full Medium Light
Adaptive leveler ✔️+ ✔️ none
Tone-shaping EQ ✔️+ ✔️ none
Loudness normalization ✔️ ✔️ none
Notch EQ ✔️ ✔️ ✔️
Crosstalk reduction ✔️ ✔️ ✔️
De-noising ✔️ ✔️ ✔️
High pass filter ✔️ ✔️ ✔️
De-esser ✔️ ✔️ ✔️

 

Here you have a simple overview of what our individual processors in our advanced AI Enhancement is doing:

  • Adaptive Leveler: Our Adaptive Leverer, levels out loudness differences in speech, both within a single track and between the individual tracks of a recording. All without affecting the background noise.
  • Tone-Shaping EQ: Voices are vastly different and have different qualities. Our tone-shaping EQ shapes the frequency content of voices to make them sound more pleasant.
  • Loudness Normalization: Normalizes the overall volume level of your entire recording to a standard target (-18 LUFS).
  • Notch EQ: Recognizes constant, pitched noise sources (such as buzzing light dimmers) and reduces them significantly.
  • Crosstalk Reduction: AI-based method for reducing crosstalk between the voice tracks.
  • De-Noising: A powerful, AI-based de-noiser that identifies and reduces background and handling noise.
  • High Pass Filter: Greatly reduces frequencies below the range of the speaking voice, e.g. electrical hum.
  • De-Esser: Removes excessive sibilance (hissing s-like sounds).

Spatial audio

If you made a recording with the Nomono Sound Capsule, you can choose to add spatial audio when enhancing in Cloud. Spatial audio will separate and fan out the voice tracks for an enhanced spatial experience when listening with headphones. This option only applies to audio recorded with a Sound Capsule using two or more Stellar Mic's.