Data
To teach our technology to recognise sounds, we have to expose it to real-world data. Quantity matters, but more importantly it is about quality, relevance and diversity.
That is why we record these sounds ourselves either in our dedicated sound lab or through responsible data gathering initiatives. We have been doing this for seven years, thus developing unrivalled expertise into audio events.
All of this expertise is captured in our proprietary data platform, which enables us to label, organise and analyse sounds in a way that has never been done before.
Algorithms
We have developed a dedicated sound recognition framework. This provides us with the tools and ability to fuel cutting edge machine learning algorithms with real world data.
Our framework extracts hundreds of ideophonic features from sounds and then through encoding, decoding and introspection is able to analyse and accurately describe high-value sound profiles.
These individual sound profiles are then embedded into our ai3™ software platform, which is licensed and integrated into virtually any consumer device, whether in the home, out and about, or on the move.
Artificial intelligence, everywhere
We envision a future where omnipresent, intelligent, context-aware computing is able to better help people by responding to the sounds around us, no matter where we are.
We are constantly mapping the full taxonomy of sound, identifying important sounds to teach our software to recognise.
But we are not stopping there. We are driven to build a system capable of teaching itself by learning from the world around it.
Our sound profiles
Our customers integrate our ai3™ software platform into a diverse range of products because of its low processor and memory requirements.
ai3™ is capable of recognising a number of sounds from the profiles that we have taught our software to recognise (and which is growing all the time). To learn more about our embedded sound recognition software, click on the button below.
How is this different from speech and music?
Speech recognition and wake words are limited by the type of sounds that the human mouth can produce, as well as conditioned by the communicative structure of human language, which can both be exhaustively mapped.
Similarly, music mostly results from physical resonance, and is conditioned by the rules of various musical genres.
So whilst the human ear and brain are very good at interpreting sounds in spite of acoustic variations, computers were originally designed to process repeatable tasks. Thus, teaching a machine how to recognise speech and music greatly benefits from such pre-defined rules and prior knowledge.
Sounds, on the other hand, can be much more diverse, unbounded and unstructured than speech and music.
Think about a window being smashed, and all the different ways glass shards can hit the floor randomly, without any particular intent or style. Or think about the difference between a long baby cry and a short dog bark, or the relative loudness of a naturally spoken conversation versus an explosive glass crash.
Now you understand why sound recognition required us to develop a special kind of expertise: collecting sound data ourselves and tackling real world sound recognition problems made us pioneering experts in understanding the full extent of sound variability.
Our software
Our embedded software platform, ai3™, is integrated into consumer products to make them more intelligent by understanding the sounds around them.
Our patents
During the course of our pioneering work we've registered multiple patent families (and we continue to do so).