CEDAR Audio is proud to announce a massive leap forward in AI-powered noise reduction with the introduction of the VoicEX voice extractor. This incorporates unique algorithmic capabilities that take it beyond standard AI-based noise reduction techniques, and it offers remarkable performance - so much so that, when hearing it for the first time, CEDAR's own audio engineers were shocked at the amount of noise removed and the quality of the retained voices.
Gordon Reid, CEDAR's Managing Director says, "A few years ago, we started developing some of the technologies that would lead us to VoicEX. We were sure that these would offer a noticeable improvement over our existing noise reduction techniques, but we didn't know to what to degree. I was stunned when I heard the output from the first prototype, and subsequent fine-tuning of the algorithm has been directed at making VoicEX achieve the best possible results over the widest range of audio. The results are remarkable, and we think that VoicEX sets a new standard for real-time audio noise reduction."
"The leap forward has been made possible by a completely new approach to voice extraction incorporating our own advances in the field of deep neural networks to identify the voices in the signal and create two audio streams - one containing just the voices, and one containing everything else. This approach makes VoicEX very simple to use. Where you might expect numerous controls, you'll find just two knobs - one to determine the loudness of the background, and the other to control the loudness of the speech. Reduce the former, and the noise goes away without affecting the timbre of the voices. Reduce the latter, and the voices go away to reveal the background. Increase either to emphasise that part of the signal. It's incredibly simple to understand and takes no time to master and use, but the results are truly amazing."
"We expect that the technology powering VoicEX will quickly lead to new products on our other platforms, so we're very excited to see where this will lead us over the coming months."
Your browser does not support the audio element. Hear VoicEX in action
VoicEX will be available initially on CEDAR Cambridge 14, which has been previewed at various security events and will be shown to the general public for the first time at the AES Conference on Audio Archiving, Preservation & Restoration (1 - 3 June, Culpeper, VA). Please contact sales@cedaraudio.com or your local CEDAR Cambridge dealer for pricing.
Once in a while a transformative technology appears. Artificial Intelligence (or AI) is one of these, and its impact on the audio industry is going to be huge.
CEDAR Audio started down the road toward AI as far back as 1994 when it introduced the DH-1 dehisser, the world's first digital broadband denoiser that didn't require an audio fingerprint. This was something that the company was often told was impossible, but the DH-1 worked, and often worked extremely well, and it proved to be a significant step forward in the art and science of noise reduction. Over the following years, the company developed improved products based upon unique data driven models, and continued to lead the world with hardware and software products that would win Emmy®, Academy®, IABM® and Cinema Audio Society awards. The introduction of the company's Learn algorithm in 2015 marked another milestone and the latest versions of this underpin the current pinnacle in zero-latency noise reduction using statistical modelling and classic signal processing techniques. But today, the introduction of deep neural networks has fuelled another leap forward, and VoicEX gives an indication of what will be possible in the future when AI is applied to all manner of audio processing requirements.
It's a new world.
CEDAR Audio Limited, 20 Home End, Fulbourn, Cambridge, CB21 5BS, United Kingdom. t: +44 1223 881771 e: sales@cedaraudio.com
News