阅读说明：本技术 一种语音命令识别的方法及装置 (Voice command recognition method and device ) 是由 陈勰 于 2019-04-30 设计创作，主要内容包括：提供了一种语音命令识别的方法及装置,其中该方法包括:接收待确定语音命令的第一音频信号(步骤21)；针对N个候选语音命令分别执行以下过程:在第一音频信号中,滤除第n个候选i吾音命令对应的第二音频信号,得到第三音频信号；将第三音频信号输入到预先训练完成的音频模型中,该音频模型用于识别输入的音频信号与背景音频信号的匹配度,得到第n个候选语音命令对应的匹配度(步骤22)；n取遍1-N的每个整数,N为大于0的整数；根据N个候选语音命令对应的匹配度,确定第一音频信号中的语音命令(步骤24)。将语音命令的识别过程转换为噪音的分类问题,可以提升语音命令识别的准确性及场景适应性。(A method and apparatus for voice command recognition are provided, wherein the method includes receiving a first audio signal of a voice command to be determined (step 21); filtering out a second audio signal corresponding to the nth candidate i wu audio command from the first audio signal to obtain a third audio signal; inputting the third audio signal into a pre-trained audio model, wherein the audio model is used for identifying the matching degree of the input audio signal and the background audio signal to obtain the matching degree corresponding to the nth candidate voice command (step 22); n is an integer from 1 to N, N is an integer greater than 0; and determining the voice command in the first audio signal according to the matching degrees corresponding to the N candidate voice commands (step 24). The recognition process of the voice command is converted into the classification problem of noise, and the accuracy and the scene adaptability of the voice command recognition can be improved.)