Offline voice recognition model updating method, household appliance, and server

Abstract

The invention discloses an offline voice recognition model updating method, a household appliance, a server and related equipment, wherein the method comprises the following steps: collecting voice data of an external environment of a household appliance; uploading the collected voice data to a server, wherein the voice data is used for indicating the server to carry out model training so as to obtain an updated voice recognition model; and receiving the updated voice recognition model sent by the server. According to the method in the invention, the server is used for collecting the voice data sent by the household appliance as training data, and model training is carried out according to the training data so as to obtain the updated voice recognition model, which is sent to the household appliance, so that the household appliance receives the updated voice recognition model sent by the server, the local offline voice recognition model can be replaced with the updated voice recognition model, so that online updating of the offline voice recognition model in the household appliance is realized, the replacement of the new and old models is completed, and the workload of offline model training of the household appliance is reduced.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an offline speech recognition model updating method, device, computer equipment and computer-readable storage medium. Background technique [0002] With the development and progress of science and technology, offline speech recognition has been widely used in people's real life, that is, the process of recognizing text or voice operations without a network. For example, users can interact with household appliances through offline voice recognition. The recognition model recognizes the user's voice, so that the home appliance performs an operation according to the recognized voice. [0003] In related technologies, an offline speech recognition model is formed from a large amount of training data and test data. However, the training data and test data used to train and test the offline speech recognition model are fixed. When training and testing the offline speech reco...

AI Technical Summary

Problems solved by technology

However, the training data and test data used to train and test the offline speech recognition model are fixed. When training and testing the offline speech recognition model based on the training data and test data in the current period, the required training time and testing time are relatively long. Long and difficult to maintain later

Images