Cambridge audio software specialist AudioTelligence has announced the launch of aiso™, a new consumer technology brand and a family of innovative products for smartphones based on its proven audio technology.
The revolutionary new approach means, for the first time, a voice interrupting a smartphone video recording or call can be removed – along with the images of the interloper – without also losing what the main speaker is saying.
The unique solution – which can be applied to a video in real time or after recording – will make it easier than ever to achieve a perfect soundtrack at the first attempt. And it could spell the end of videoconferencing interruptions for people working from home in busy households.
"The technology is compatible with any video call or video meeting app such as Zoom and Microsoft Teams, with all sounds originating from outside the camera's field of view automatically discarded in real time," said Ken Roberts, CEO of AudioTelligence.
"And it makes sound editing your TikTok or YouTube video as easy as framing the subject in a photo. The user simply pinches and zooms to select a rectangular area of the video containing the target sound sources. Interfering voices from outside this area are then removed from the audio."
As part of its new aiso™ consumer technology brand, AudioTelligence is initially launching two product lines for smartphones, optimised for two different applications – video recording or video calls. Each product line offers two features: AudioCrop™ and AudioTag are designed for smartphone videos, with CallCrop™ and CallTag™ aimed at video calls and videoconferencing.
For smartphone videos, AudioCrop™ or AudioTag can both be used to select the desired audio either in real time or during post-processing. AudioCrop™ allows a specific part of a video frame to be selected, with audio and/or visual interruptions from outside that area removed – while AudioTag allows specific sound sources to be selected based on their location, with all other sound sources discarded.
For video calls or videoconferences, users can choose a new CallCrop™ or CallTag™ sound option in video meeting apps, alongside the standard internal microphone and Bluetooth headset options. Again, CallCrop™ focuses on a particular part of the video frame, with CallTag™ focusing on an individual sound source.
Existing 'audio zoom' solutions are limited as they are based on beamforming technology, which makes them imprecise – only capable of focusing audio capture within a range of tens of degrees. In contrast, the aiso™ products use blind source separation (BSS) technology, which is more effective at separating target sound sources from interfering ones. And unlike noise suppression technology, BSS is uniquely valuable when there are overlapping speech signals – if new sources appear, they can also be eliminated. Importantly, BSS works even when the source of interest isn’t dominant.
The AudioTelligence BSS technology improves the signal-to-interference ratio by up to 25 decibels (dB) on a three-microphone smartphone.
The aiso™ family of products is a flexible, software-only solution designed to work on any multi-microphone Android smartphone or tablet – the lightweight embedded software is simple for smartphone OEMs to integrate into their devices. It does not require a dedicated hardware codec or DSP and it works with standard microphones, without the need for special microphone positioning.
The aiso™ family of products is available now for licensing to smartphone and tablet manufacturers and developers.