A voice recognition method for acquiring speech content of a user of a vehicle and estimating an object mentioned in the speech content, the voice recognition method comprising: acquiring (S1) at least one of an output signal of a sensor mounted on the vehicle and a control signal for a device mounted on the vehicle as an input signal; identifying an expression representing a state or a position according to the speech content (S3); detecting the state or position of the candidate of the object on the basis of the input signal (S5); and estimating, as an object mentioned in the speech content, the candidate of the object corresponding to the state or position recognized from the speech content (S6).
一种声音识别方法,用于获取车辆的使用者的讲话内容来估计在讲话内容中提及的对象物,该声音识别方法包括以下步骤:将搭载于车辆的传感器的输出信号和针对搭载于车辆的设备的控制信号中的至少一方作为输入信号来获取(S1);根据讲话内容来识别表示状态或位置表达(S3);基于输入信号来检测对象物的候选的状态或位置(S5);以及将与根据讲话内容识别出的状态或位置相符的对象物的候选估计为在讲话内容中提及的对象物(S6)。
Voice recognition method and voice recognition device
声音识别方法和声音识别装置
2024-09-06
Patent
Electronic Resource
Chinese
VOICE RECOGNITION DEVICE, VOICE RECOGNITION METHOD, AND VOICE RECOGNITION PROGRAM
European Patent Office | 2024
|VOICE RECOGNITION DEVICE, VOICE RECOGNITION METHOD, AND VOICE RECOGNITION PROGRAM
European Patent Office | 2022
|Voice recognition device, voice recognition method, and voice recognition program
European Patent Office | 2024
|