Voice wake-up method, device and computer equipment based on artificial intelligence

Abstract

The present application proposes an artificial intelligence-based voice wake-up method, device, and computer equipment. The artificial intelligence-based voice wake-up method includes: performing windowing and framing operations on the online recorded voice to obtain at least one voice frame; The speech frame is subjected to feature extraction to obtain the speech feature; the static speech feature contained in the speech frame is calculated by the speech wake-up model based on the convolutional neural network, and the static speech feature contained in the speech frame is obtained corresponding to the non-wake word category and the posterior probability of the wake-up word category; when the posterior probability corresponding to the wake-up word category contained in the speech frame is greater than or equal to a predetermined threshold, it is determined that the online recorded voice includes the wake-up word. The present application can effectively reduce the parameter amount of the voice wake-up model based on the convolutional neural network, so as to achieve the purpose of reducing the amount of computation, and the present application can improve the effect of voice wake-up.

Description

technical field [0001] The present application relates to the technical field of voice recognition, in particular to an artificial intelligence-based voice wake-up method, device and computer equipment. Background technique [0002] In smart home or voice interaction systems, voice wake-up (wakeword) technology is widely used. However, the effect and calculation of voice wake-up greatly reduce the actual application experience of voice wake-up, and increase the requirements of voice wake-up on device hardware. For example, if the false wake-up rate of voice wake-up is greater than a threshold in the application, such as 1 / 3 Such a frequency of false wake-up triggers may arouse user disgust; on the other hand, if the computing power of voice wake-up exceeds the computing power of some low-end chips, it will restrict the use of voice wake-up technology in many products. [0003] In the existing related technologies, the technology used for voice wake-up is the keyword-spottin...

AI Technical Summary

Problems solved by technology

[0004] However, the voice wake-up technology of the above keyword recognition method has a large amount of model parameters, and for different wake-up words, the design of the filler (filler) must be changed, and the corresponding decoding parameters and detected tricks must be adjusted. It is difficult to have a unified algorithm to ensure that the effect of each wake-up word is at a stable level, and after the filler is set, the misrecognition level of the wake-up word is fixed, and it is not possible to flexibly and conveniently correct the misrecognition Wake words for tuning and learning

Images