In Summary
Known for intelligent tools that flash their AI credentials, Sonible’s new smart:deess takes on de-essing with a twist of its own. With automatic parametrization, and non-level dependent treatments on offer, it offers an alternative to classical de-essing.
Going Deeper
What’s In An Ess?
Known to many, the ‘classical’ de-esser was developed to clamp down on distracting fricative sounds such as the “s” and “t” sounds found in many languages. Essentially using frequency sensitive compression, most devices use their own take on this basic MO. Although most use some kind of detector tuned to the target frequency, some go further by also using split-band processing for the output resulting in more transparent treatments.
Like all classical dynamic processing, these devices have typically relied on a user-set threshold to determine when the action kicks in.
Sonible smart:deess
Taking a different approach, Sonible are known for their use of AI tech for a number of audio processing problem solvers. This time, they have used their knowhow to create an intelligent de-esser. With smart:deess, the entire sibilant is processed rather than just its loudest peak, with Sonible claiming more natural sounding results compared to level-based devices.
Another headline feature is smart:deess’ ability to identify specific phonemes. This means that other linguistic building blocks such as plosives can be caught as well as higher band fricatives. It does all this in real time and determines the exact start and end point of each event.
In the video we try smart:deess on speech. We explain its modes as well as its other controls. These set it apart from classical processors as we check out its threshold-less operation with detailed spectrogram feedback.
Smart:deess Key Features:
Natural-sounding de-essing based on AI technology.
De-essing and plosive reduction in one tool.
Real-time phoneme detection to identify sibilants and plosives.
Harsh sounds can be shaped, rather than ‘just turned down,’ via spectral processing.
Processes the entire sibilant from start to finish, without the need to set a threshold.
Handles different phonemes – S, Z, Sh, Ch, K, T, P – each with distinct processing.
Will automatically “re-ess” to improve any ‘dull’ and ‘lisping’ phonemes.
Smart:deess is now available at an introductory price of €89 (regular price €129) until 1st December 2023. All prices are inclusive of VAT. Personalized upgrade pricing is available for existing Sonible customers.
A Word About This Article
As the Experts team considered how we could better help the community we thought that some of you are time poor and don’t have the time to read a long article or a watch a long video. In 2023 we are going to be trying out articles that have the fast takeaway right at the start and then an opportunity to go deeper if you wish. Let us know if you like this idea in the comments.