Cambridge Innovation Capital and Cambridge Enterprise fund spinout that makes speech clear and intelligible in a noisy world
Cambridge startup AudioTelligence has raised £3.1m in funding from Cambridge Innovation Capital and Cambridge Enterprise to grow its team to meet the considerable demand for its technology which, in addition to helping humans to hear and understand speakers in the presence of loud background noise, helps to improve the performance of voice recognition systems.
Although the technology was initially developed by CEDAR Audio, world leaders in the related fields of audio restoration and dialogue noise suppression, the CEDAR team recognised that it required a different business model. So they decided to spin out a new company, AudioTelligence, to license the technology for consumer products. At this point, it was clear that a sizeable funding round was required to enable the company to secure contracts with industry leaders, and the team looked to Cambridge Innovation Capital (CIC) for support. CIC was established to help companies with significant IP and strong Cambridge connections to stay and grow within the Cambridge cluster, which is the ‘centre of the universe’ for voice command and control technologies. (In recent years Amazon, Google and Apple have all set up R&D centres in the city to integrate this technology into their products and services.) Andrew Williamson, Investment Director for CIC, sees a considerable opportunity for AudioTelligence and says that Cambridge is the best place for it to build the strong team it needs. He says:
“The cluster has specialist expertise in voice recognition and signal processing based on decades of research and engineering. AudioTelligence is very well connected with the university and already has considerable technical and commercial expertise. It is well placed to capitalise on the opportunity to provide a digital solution for voice driven applications.”
AudioTelligence is also a good fit for Cambridge Enterprise because the technology has spun out of the university and has a strong social benefit through its potential use in hearing assistance devices. Elaine Loukes, Investment Manager at Cambridge Enterprise commented,
“AudioTelligence is a spin-out from CEDAR Audio, which is the oldest company in our portfolio, and was the first to make a return for us. It’s a real pleasure to be working with a new company that we know to have such an excellent pedigree.”
AudioTelligence technology is unique because, instead of using high quality microphones to help distinguish the target voices from background noise, it uses a data driven approach called blind audio signal separation. It doesn’t require matched microphones, which makes it cheaper and easier to implement, it doesn’t require the user to train the algorithm, and it offers high performance with very low latency. Furthermore, the system is adaptive so, if new noises appear, these are also eliminated from the sound heard by the listener. The resulting sound is high quality with no artefacts or echo.
Its performance is impressive. When reading a list of 100 items to an Amazon Echo Dot using existing technology, the device will recognise 84 items under good conditions, but this drops to 22 when a second, interfering sound source is introduced. Using AudioTelligence software to pre-process the sound enables the system to recognise 94 items even when the interference is present.
AudioTelligence technology will be available on a licensing basis, offering low-cost, high quality solutions for devices such as voice activated navigation and entertainment systems, personal assistants and hearing assistance devices.