What exactly is AMSI?
In Zoundream, we've spent several months to determine the best solution to identify and translate a human produced sound into its actual meaning, specifically for children pre-speech. There are several approaches in Machine Learning literature to address this challenge, but unfortunately none of them is actually suitable to work on a continuous incoming stream of audio. So we created our custom deep-learning based solution. AMSI, which is an acronym for Acoustic MultiStage Interpreter, processes the sound into a series of inner deep-learning models to extract the meaning of a baby cry. Think about understanding letters, then words, then meaningful sentences. That's exactly what AMSI does. AMSI can be adapted to many different problems and shortly we'll be able to indentify pathologies and uncommon behaviours of the baby.
Designed by parents
Technology development driven by parents. Constantly tested with hundred of families ensuring fit with real families needs.
Built on solid paediatric research and studies
Paediatric and scientific experts define and review every single step of development. We collaborate with hospitals and research studies, all around the world.
Wide hardware scalability
AMSI has been designed to run on a variety of different hardware’s and platforms: potentially any connected device with a microphone.
Most advanced technology for cry analysis - globally
After years of studies and research, AMSI technology benchmarks strongly as the leading technology globally, for the specific field of cry analysis.
Over 100k hours testing with actual newborns
AMSI technology is tested and used by actual parents with their newborns. As of beginning 2021, we totalled over 100 thousands hours of testing – and counting.
Largest cry dataset in the world
Thanks to extensive testing for several years, Zoundream collected the most extensive dataset – globally – to boost our very specific field of application.
Adapting Our Technology in Your Product
AMSI is now a mature platform that we offer to partners. Initially, we prototyped AMSI on a hardware device that was used for testing purposes only. This constraint required us to optimize the AMSI engine for various potential architectures, including embedded hardware platforms and mobile systems. However, we have now migrated AMSI to a remote service-based solution to take advantage of the increased computational power of cloud computing and provide even more accurate results.