Method for training wake-up model and device thereof

Abstract

The invention provides a method for training a wake-up model and a device thereof, and the method comprises the steps: obtaining a first training set and a second training set when the model trainingis triggered; respectively inputting the first training set into an initial acoustic model and a current acoustic model, and determining a first difference parameter by comparing output results of theinitial acoustic model and the current acoustic model; inputting the second training set into a current acoustic model, and determining a second difference parameter by comparing an output result ofthe current acoustic model with a one-hot code corresponding to wake-up voice which can be recognized by the current acoustic model; and adjusting model parameters of the current acoustic model according to the first difference parameter and the second difference parameter. By utilizing the method provided by the invention, the current acoustic model can be compatible with the initial voice underthe condition of ensuring that the current acoustic model adapts to the current scene, the risk of unstable performance of the wake-up model caused by updating is reduced, and the trained acoustic model is well compatible with the previous initial wake-up scene on the premise of adapting to a more complex scene.

Description

technical field [0001] The invention relates to the technical field of speech processing, in particular to a method and device for training an awakening model. Background technique [0002] With the continuous development of technology, smart devices are becoming more and more popular. Existing smart devices can determine whether to wake up the smart device by receiving the voice signal input by the user. One of the application scenarios is that the smart device can The model recognizes the voice signal input by the user to wake up the smart device in the waiting state. When the acoustic model can recognize the input voice signal, the smart device is woken up, so that the user can realize other smart home devices through the awakened smart device. control. Among them, the user pre-records the wake-up voice to the smart device in advance, and the smart device performs model training according to the recorded wake-up voice to generate an acoustic model. When the smart device ...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method and device for training the wake-up model, which is used to solve the existing technology. It is better to retrain the new acoustic model after continuously collecting new wake-up word data and mixing it with the previously recorded wake-up word data. The performance model replaces the previous model with a large amount of training, and it takes a long time to retrain the acoustic model, and because the wake-up model needs to be re-established, and the proportion of training data is not well controlled, the actual wake-up effect of the re-trained wake-up model is not stable.

Images