RECHO technology
The technology backing RECHO exploits the non-linear oscillations effects within the sensing mechanisms of microphone or other sensors to directly extract features of time series signals for machine learning. As such, computing power hungry machine learning training and inference could be operated purely on the smart audio device (i.e., Google Home, Apple Homepod, Amazon Alexa, etc.) locally using very limited samples without the need cloud-based data center and high performance computers. The computing system will be more securer and more human centric.
Reference: Shougat, M. R. E. U., Li, X., Mollik, T., & Perkins, E. (2021). A Hopf physical reservoir computer. Scientific Reports, 11(1), 1-13.
Shougat, M. R. E. U., Li, X., Shao, S., McGarvey, K., & Perkins, E. (2022). Hopf oscillation-based reservoir computer for reconfigurable sound recognition.  arXiv:2212.10370
The Physical Reservoir (PR)
The physical reservoir is mapping the 1D time series signal into a features enriched signal with its intrinsic non-linear and resonances effects and interpret with a simple ML model.
Standard transducer
RECHO transducer
Original audio signal
Recho outputs
Recovered signal
RECHO developed a technology that could reconstruct and enhance the audio signal using the original outputs from RECHO PR transducing devices. This technology allows RECHO to be an ubiquitous solution for edge signal intelligence devices while keeping superior recording qualities.
Performance comparison
Compared to state-of-the-art solutions, echosonic produces >99% (97% for other solutions) of accuracy on three class wake words recognition, while draws <15% power consumption. More important, we only need to use <10% of data to reconfigure the RECHO inferencing engine, enables reconfiguring devices directly on the edge.