System and method for identifying a vehicle via audio signature matching
A method includes receiving audio signal features generated by neural network feature extraction, identifying a vehicle type by neural network feature recognition, and determining a risk level of a vehicle driver based on the vehicle type. A computing system includes a processor and a memory storing instructions that when executed cause the computing system to receive audio signal features generated by neural network feature extraction, identify a vehicle type by neural network feature recognition, and determine a risk level of a vehicle driver based on the vehicle type. A non-transitory computer readable medium contains instructions that when executed cause a computer to receive audio signal features generated by neural network feature extraction, identify a vehicle type by neural network feature recognition layer and determine a risk level of a vehicle driver based on the vehicle type.
1. A computer-implemented method comprising:
receiving a set of raw audio signals associated with a vehicle at a feature extraction layer of a trained neural network;
generating a set of audio signal features from the set of raw audio signals by using the feature extraction layer of the trained neural network, the set of audio signal features representing audio data in which information private to an operator of the vehicle has been removed;
analyzing the set of audio signal features to identify a type of the vehicle by using a feature recognition layer of the trained neural network; and
determining a level of risk associated with the operator of the vehicle based upon the type of the vehicle.
2. The computer-implemented method of claim 1 , wherein generating the set of audio signal features includes generating audio signal features from which no original audio content can be recreated or derived.
3. The computer-implemented method of claim 1 , wherein analyzing the set of audio signal features to identify the type of the vehicle includes identifying one or more of: a make of the vehicle, a model of the vehicle, a class of the vehicle, or a sub-model of the vehicle.
4. The computer-implemented method of claim 1 , wherein determining the level of risk associated with the operator of the vehicle based upon the type of the vehicle includes determining an aggregate risk with respect to a family or household.
5. The computer-implemented method of claim 1 , wherein determining the level of risk associated with the operator of the vehicle based upon the type of the vehicle includes setting or adjusting a premium of an insurance policy.
6. The computer-implemented method of claim 1 , wherein determining the level of risk associated with the operator of the vehicle based upon the type of the vehicle includes determining an identity of a driver in a multi-vehicle household.
7. The computer-implemented method of claim 1 , further comprising storing an historical record including the type of the vehicle and identifying information of the vehicle.
8. The computer implemented method of claim 1 , wherein the trained neural network is trained using a labeled set of raw audio training signals from a number of different vehicles.
9. The computer-implemented method of claim 8 , wherein the number of different vehicles corresponds to a subset of vehicle types associated with the operator of the vehicle.
10. The computer-implemented method of claim 9 , further comprising identifying the subset of vehicle types associated with the operator of the vehicle by reference to one or both of: (i) an insurance policy associated with the operator of the vehicle, and (ii) a region where the operator of the vehicle is located.
11. A computing system comprising:
one or more processors; and
one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to:
receive a set of raw audio signals associated with a vehicle at a feature extraction layer of a trained neural network;
generate a set of audio signal features from the set of raw audio signals by using the feature extraction layer of the trained neural network, the set of audio signal features representing audio data in which information private to an operator of the vehicle has been removed;
analyze the set of audio signal features to identify a type of the vehicle by using a feature recognition layer of the trained neural network; and
determine a level of risk associated with the operator of the vehicle based upon the type of the vehicle.
12. The computing system of claim 11 , wherein the instructions, when executed by the one or more processors, that cause the computing system to generate the set of audio signal features further include instructions that cause the computing system to generate audio signal features from which no original audio content can be recreated or derived.
13. The computing system of claim 11 , wherein the instructions, when executed by the one or more processors, that cause the computing system to analyze the set of audio signal features to identify the type of the vehicle further include instructions that cause the computing system to identify one or more of: a make of the vehicle, a model of the vehicle, a class of the vehicle, or a sub-model of the vehicle.
14. The computing system of claim 11 , wherein the instructions, when executed by the one or more processors, that cause the computing system to determine the level of risk associated with the operator of the vehicle based upon the type of the vehicle further include instructions that cause the computing system to determine an aggregate risk with respect to a family or household.
15. The computing system of claim 11 , wherein the instructions, when executed by the one or more processors, that cause the computing system to determine the level of risk associated with the operator of the vehicle based upon the type of the vehicle further include instructions that cause the computing system to set or adjust a premium of an insurance policy.
16. The computing system of claim 11 , wherein the instructions, when executed by the one or more processors, that cause the computing system to determine the level of risk associated with the operator of the vehicle based upon the type of the vehicle further include instructions that cause the computing system to determine an identity of a driver in a multi-vehicle household.
17. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to:
receive a set of raw audio signals associated with a vehicle at a feature extraction layer of a trained neural network;
generate a set of audio signal features from the set of raw audio signals by using the feature extraction layer of the trained neural network, the set of audio signal features representing audio data in which information private to an operator of the vehicle has been removed;
analyze the set of audio signal features to identify a type of the vehicle by using a feature recognition layer of the trained neural network; and
determine a level of risk associated with the operator of the vehicle based upon the type of the vehicle.
18. The non-transitory computer readable medium of claim 17 , wherein the instructions, when executed by the one or more processors, that cause the one or more processors to generate the set of audio signal features further cause the one or more processors to generate audio signal features from which no original audio content can be recreated or derived.
19. The non-transitory computer readable medium of claim 17 , wherein the instructions, when executed by the one or more processors, that cause the one or more processors to analyze the set of audio signal features to identify the type of the vehicle further cause the one or more processors to identify one or more of: a make of the vehicle, a model of the vehicle, a class of the vehicle, or a sub-model of the vehicle.
20. The non-transitory computer readable medium of claim 17 , wherein the instructions, when executed by the one or more processors, that cause the one or more processors to determine the level of risk associated with the operator of the vehicle based upon the type of the vehicle further cause the one or more processors to set or adjust a premium of an insurance policy.