CEDAR debuts ‘radical’ noise reduction algorithm
The latest module for the CEDAR Cambridge audio restoration system is based on a noise reduction algorithm described as ‘radical’ by its developer, CEDAR Audio. According to the UK-based company, the FNR module – part of the newly announce CEDAR Cambridge V10 – is ‘capable of performance that would have seemed impossible just a few years ago’.
Designed to clean up speech recordings suffering from very poor signal to noise ratios, FNR is likely to prove popular within the audio forensic and security fields as well as post and broadcast. Alan French, head of the manufacturer’s forensic and security division, pointed to ‘the problem of revealing and increasing the intelligibility of voices recorded in crowded cafés and similar environments’, as the main reason. ‘We in the forensic audio community encounter this problem time and again and, while the venues and scenarios may vary greatly from case to case, they all share a common difficulty; how do you reveal a wanted speaker when the signal to noise ratio is very poor, or if the unwanted sound on the recording is actually other human voices?’
He continued, ‘FNR is adaptive, it reacts – and reacts quickly – to changes in the background noise in café-type recordings, and it doesn't have anything like as much effect on the wanted voices as previous filtering systems. I have been testing FNR for more than six months prior to its release, and it has yielded excellent results on genuine casework. It also works very well on recordings made in moving vehicles because, as in the café scenario, the background noises (primarily, the engine and road noise) are constantly changing, and FNR tracks these changes better than anything else I've yet heard.’
Alongside FNR, CEDAR Cambridge V10 includes Retouch 7 and DNS One with Learn, both of which debuted in the CEDAR Studio 7 suite. Additionally, a new ‘history’ feature means that when a session is saved, the complete undo/redo stack is also saved, so that users can later reload the session and step back all the way to the first time the audio was loaded. Video files can also now be loaded and run alongside audio files, assisting postproduction engineers. Other features include extended hot keys, improvements in the batch processor, and improved layouts to facilitate internationalisation.