System and method for incorporating gesture and voice recognition into a single system
AssigneeHonda Motor Co., Ltd.
InventorsPedram Vaghefinazari, Stuart Yamamoto, Tarek El Dokor, Josh Tyler King
Life of this patent
Estimating the term…
Abstract
A system and method for combining two separate types of human machine interfaces, e.g., a voice signal and a gesture signal, performing voice recognition to a voice signal and gesture recognition to the gesture signal. Based on a confidence determination using the voice recognition result and the gesture recognition result the system can, for example, immediately perform the command/request, request confirmation of the command/request or determine that the command/request was not identified.
Claims22
A computer based method for executing a command in a vehicle, comprising the steps of:
- receiving a voice signal;
- receiving a gesture signal;
- performing a voice recognition procedure to generate a voice recognition (VR) score representing a likelihood that the voice signal corresponds to a first voice command;
- performing a gesture recognition procedure to generate a gesture recognition (GR) score representing a likelihood that the gesture signal corresponds to a first gesture command;
- and
- executing a first command in a vehicle corresponding to said first voice command and first gesture command when said voice recognition score exceeds a first threshold and said gesture recognition score exceeds a second threshold.
A computer based method for executing a command in a vehicle, comprising the steps of:
- receiving a voice signal;
- receiving a gesture signal;
- performing a voice recognition procedure to generate a voice recognition (VR) score representing a likelihood that the voice signal corresponds to a first voice command;
- performing a gesture recognition procedure to generate a gesture recognition (GR) score representing a likelihood that the gesture signal corresponds to a first gesture command;
- generating a combined recognition score based on a combination of said VR score and said GR score;
- and
- executing a first command in the vehicle corresponding to at least one of said first voice command and said first gesture command when said combined recognition score exceed a first threshold.
A non-transitory computer readable medium comprising computer executable code which when executed by a computer performs the steps of:
- receiving a voice signal;
- receiving a gesture signal;
- performing a voice recognition procedure to generate a voice recognition (VR) score representing a likelihood that the voice signal corresponds to a first voice command;
- performing a gesture recognition procedure to generate a gesture recognition (GR) score representing a likelihood that the gesture signal corresponds to a first gesture command;
- executing a first command in a vehicle corresponding to said first voice command and first gesture command when said voice recognition score exceeds a first threshold and said gesture recognition score exceeds a second threshold.
A non-transitory computer readable medium comprising computer executable code which when executed by a computer performs the steps of:
- receiving a voice signal;
- receiving a gesture signal;
- performing a voice recognition procedure to generate a voice recognition (VR) score representing a likelihood that the voice signal corresponds to a first voice command;
- performing a gesture recognition procedure to generate a gesture recognition (GR) score representing a likelihood that the gesture signal corresponds to a first gesture command;
- generating a combined recognition score based on a combination of said VR score and said GR score;
- and
- executing a first command in a vehicle corresponding to at least one of said first voice command and said first gesture command when said combined recognition score exceed a first threshold.
A system for executing a command in a vehicle comprising:
- a microphone positioned in the vehicle, for receiving a voice signal;
- a optical sensing device, positioned in the vehicle, for receiving a gesture signal;
- a processor for performing a voice recognition procedure to generate a voice recognition (VR) score representing a likelihood that the voice signal corresponds to a first voice command, the processor for performing a gesture recognition procedure to generate a gesture recognition (GR) score representing a likelihood that the gesture signal corresponds to a first gesture command;
- and
- an execution unit positioned in the vehicle, for executing a first command corresponding to said first voice command and first gesture command when said voice recognition score exceeds a first threshold and said gesture recognition score exceeds a second threshold.
Dependencies are inferred from the claim text.