First software platform turning any machine sounds and
vibrations into actionable meaning at the edge
Value demonstrated in hours.
Only a few hours are needed to evaluate Otosense ability to identify events and anomalies on a given machine.
Otosense can learn to identify any stationary or transient sound or vibration
Real-time event recognition on the edge without using any network connection.
Otosense learns the behavior of any machine, and keeps learning over time.
An anomaly detected today becomes an identified event tomorrow.
"OtoSense gives the possibility of tagging a given sound segment which contains the noise sources the user wants to identify.
Each expert of a specific noise issue has "taught" the Otosense machine using their PSA automotive sound knowledge.
Today, we are able to recognize noises from engine, cabin (HVAC), wheels, etc.
OtoSense can deal with many different situations and contexts."
-Head of R&D Department
"OtoSense is working with major automakers on software that could give cars their own sense of hearing to diagnose themselves before any problem gets too expensive. The technology could also help human-driven and automated vehicles stay safe, for example by listening for emergency sirens or sounds indicating road surface quality.
OtoSense has developed machine-learning software that can be trained to identify specific noises, including subtle changes in an engine or a vehicle’s brakes."
-MIT Technology Review
MONITOR ANY EVENT ON ANY MACHINE
OtoSense is not limited to the monitoring of continuous, steady sounds or vibrations. Any short, transient event can be characterized and identified as well, even in complex environments. The constant learning process allows growing the number of events Identified over time, turning each anomaly into an identifiable, known event over time.
USING ANY VIBRATION/SOUND SENSOR
Accelerometer, piezo crystal, MEMS microphone, pressure sensor, laser-based vibration sensor... any sensor delivering an analog or digital time series can be processed by OtoSense edge software. Sample rates from 50Hz to 392kHz can be used.