DeRoom is a Machine-Learning based audio plug-in to reduce or remove reverb and room resonances in real-time. An artificial neural network has been trained on many different room scenarios in order to be able to separate direct sound from reflection components. Reverb tails and echos are automatically detected and then precisely suppressed or if desired entirely removed. DeRoom is perfectly suited to increase the quality and intelligibility of speech which has been recorded in very reverberant environments.
No need to estimate and set room timing constants by hand. The algorithm will figure it out internally in an automatic fashion. Only set the reduction amount and let the neural network remove the unwanted reverb.
Fine-tune the results by selecting between three different room types: Small, Medium and Large. The algorithms are developed in individual optimization sessions and can be easily compared against each other.
Chameleon is being used to match dialogue recorded in a studio to recordings in different locations
Chameleon is being used to match foley to a dialogue recording in an underground parking lot
Chameleon is being used to match a dry hihat-sample to a real drum-set by imitating the reverb of the recording room
Chameleon is being used to increase the reverb amount of a guitar recording. The existing reverb is imitated and boosted.