INTELLIGENT VOICE RECOGNIZING METHOD APPARATUS AND INTELLIGENT COMPUTING DEVICE

摘要

A method for intelligently recognizing a voice by a voice recognition device is disclosed. The intelligent speech recognition method of a speech recognition apparatus according to an embodiment of the present invention obtains a first noise level for an environment in which the speech recognition apparatus is located, and inputs the first noise level to a pre-trained noise-sensitivity model to obtain a second noise level. 1 Obtain an optimal sensitivity and recognize the user's voice based on the first optimal sensitivity, but the noise-sensitivity model is learned in a plurality of noise environments in which different noise levels are obtained, so that the IoT device (speech recognition device) When it is in operation, it is possible to accurately obtain the optimal sensitivity corresponding to the noise level according to the operating state. At least one of the voice recognition apparatus and the intelligent computing device of the present invention is an artificial intelligence module, a drone (Unmanned Aerial Vehicle, UAV), a robot, an augmented reality (AR) device, a virtual reality (VR) ) devices, devices related to 5G services, and the like.