According to its creators, Cedar Audio’s new VoicEX voice extractor is ‘close to being a magic button and is so simple to use that novices and experts alike can achieve results that would have been unthinkable just a few months ago’.

‘Some time back, we started developing the AI-based DNN (deep neural network) technologies used in VoicEX,’ says Cedar Audio MD, Gordon Reid.

‘We were sure that these would offer a noticeable improvement over our existing noise reduction technologies, although we didn’t know to what degree. But we were stunned when we first heard VoicEX, and the past few months have been spent creating a version for all of our plug-in customers.

‘Today, we’re delighted to announce our VoicEX plug-in for VST, AU and AAX platforms. The results that users can obtain from this are remarkable, and it sets a new standard for real-time noise reduction.’

Cedar says that the step forward has been made possible by adopting a completely new approach to voice extraction – rather than trying to gauge the noise level at each frequency and suppress this, an algorithm called a neural network is trained to identify the voices in the signal and create two audio streams, one of which contains just the voices, and the other containing everything else. This approach makes VoicEX very simple to use. Where numerous controls might be expected, find are two knobs: one to determine the loudness of the background, and the other to control the loudness of the speech. Reducing the former to makes noise and excessive reverberation go away. Reducing the latter, makes the voices go away. Increasing either emphasises that part of the signal.

‘It’s incredibly simple to use and takes no time at all to master, but the results can be truly amazing,’ Reid enthuses.

VoicEX is available immediately.

More: www.cedaraudio.com