Voice recognition method and voice recognition device
AssigneeNissan Motor Co., Ltd.
InventorAtsunobu Kaminuma
Life of this patent
Estimating the term…
Abstract
A voice recognition method for acquiring utterance content of a user of a vehicle and estimating a target object mentioned in the utterance content, the voice recognition method including: acquiring, as an input signal, at least one of a control signal of a device mounted on the vehicle and an output signal of a sensor mounted on the vehicle; recognizing an expression representing a state or a position from the utterance content; detecting a state or a position of a candidate of the target object, based on the input signal; and estimating a candidate of the target object fitting a state or a position recognized from the utterance content to be a target object mentioned in the utterance content.
Claims19
A voice recognition method for acquiring utterance content of a user of a vehicle and estimating at least one target object mentioned in the utterance content, the voice recognition method comprising:
- acquiring, as an input signal, at least one of a control signal of a device mounted on the vehicle and an output signal of a sensor mounted on the vehicle;
- converting the acquired control signal or the acquired output signal into a specific data form predetermined to represent a detected situation;
- recognizing an expression representing a state or a position of the at least one target object from the utterance content and extracting a keyword indicating the state or the position of the at least one target object mentioned in the utterance content;
- referring to a command list in which information about candidates of the at least one target object, keywords related to the candidates, and information specifying input signals used in detection of states or positions of the candidates are recorded in associated with one another;
- detecting a state or a position of a candidate of the at least one target object based on the information specifying an input signal corresponding to the extracted keyword, the information being recorded in association in the command list;
- determining whether or not the state or the position recognized from the utterance content and indicated by the extracted keyword fits the state or the position of the candidate of the at least one target object detected based on the input signal;
- estimating a candidate of the at least one target object fitting the state or the position recognized from the utterance content to be the at least one target object mentioned in the utterance content;
- outputting a response command, wherein the response command is a command signal that causes the at least one target object to perform a predetermined operation,
- wherein the at least one target object is a window installed in a door of the vehicle, a braking device of the vehicle, or an engine of the vehicle;
- and
- performing, by the window, braking device, or engine, the predetermined operation in response to the command signal.
A voice recognition device configured to acquire utterance content of a user of a vehicle and estimate a target object mentioned in the utterance content, the voice recognition device including a controller configured to execute processing comprising:
- acquiring, as an input signal, at least one of a control signal of a device mounted on the vehicle and an output signal of a sensor mounted on the vehicle;
- converting the acquired control signal or the acquired output signal into a specific data form predetermined to represent a detected situation;
- recognizing an expression representing a state or a position of the at least one target object from the utterance content and extracting a keyword indicating the state or the position of the at least one target object mentioned in the utterance content;
- referring to a command list in which information about candidates of the at least one target object, keywords related to the candidates, and information specifying input signals used in detection of states or positions of the candidates are recorded in associated with one another;
- detecting a state or a position of a candidate of the at least one target object based on the information specifying an input signal corresponding to the extracted keyword, the information being recorded in association in the command list;
- determining whether or not the state or the position recognized from the utterance content and indicated by the extracted keyword fits the state or the position of the candidate of the at least one target object detected based on the input signal;
- estimating a candidate of the at least one target object fitting the state or the position recognized from the utterance content to be the at least one target object mentioned in the utterance content;
- outputting a response command, wherein the response command is a command signal that causes the at least one target object to perform a predetermined operation,
- wherein the at least one target object is a window installed in a door of the vehicle, a braking device of the vehicle, or an engine of the vehicle;
- and
- performing, by the window, braking device, or engine, the predetermined operation in response to the command signal.
Dependencies are inferred from the claim text.