Cloud based adaptive learning for distributed sensors
AssigneeTexas Instruments Incorporated
InventorsLin Sun, Wei Ma
Life of this patent
Estimating the term…
Abstract
A low power sound recognition sensor is configured to receive an analog signal that may contain a signature sound. Sound parameter information is extracted from the analog signal and compared to a sound parameter reference stored locally with the sound recognition sensor to detect when the signature sound is received in the analog signal. A trigger signal is generated when a signature sound is detected. A portion of the extracted sound parameter information is sent to a remote training location for adaptive training when a signature sound detection error occurs. An updated sound parameter reference from the remote training location is received in response to the adaptive training.
Claims16
A method for operating a sound recognition sensor, the method comprising:
- receiving an analog signal that may contain a signature sound;
- extracting sound parameter information from the analog signal;
- comparing the sound parameter information to a sound parameter reference stored locally with the sound recognition sensor to detect when the signature sound is received in the analog signal;
- generating a trigger signal when a signature sound is detected;
- sending a portion of the extracted sound parameter information to a remote training location for adaptive training when a signature sound detection error occurs;
- and
- receiving an updated sound parameter reference from the remote training location in response to the adaptive training.
A method for operating a sound recognition system, the method comprising:
- receiving at a training location for adaptive training a set of extracted sound parameters from a distributed sound sensor;
- performing an adaptive training operation on a sound parameter reference using the set of extracted sound parameters;
- and
- sending an updated sound parameter reference from the training location to the distributed sound sensor in response to the adaptive training.
An apparatus for recognizing a sound, the apparatus comprising:
- a microphone;
- an analog front end section configured to receive an analog signal from the microphone that may contain a signature sound and to extract sound parameter information from the analog signal;
- a digital classification section coupled to the analog front end section being configured to compare the sound parameter information to a sound parameter reference stored in memory coupled to the digital classification section to detect when the signature sound is received in the analog signal and to generate a trigger signal when a signature sound is detected;
- and
- a wireless link interface controlled by an application processor, wherein the wireless link interface is operable to send a portion of the extracted sound parameter information to a remote training location for adaptive training when a signature sound detection error occurs;
- and configured to receive an updated sound parameter reference from the remote training location in response to the adaptive training.
Dependencies are inferred from the claim text.