Voice wake-up method and device based on artificial intelligence

Abstract

The present invention proposes an artificial intelligence-based voice wake-up method and device, wherein the voice wake-up method includes: acquiring pronunciation information corresponding to a custom wake-up word; acquiring approximate pronunciation information corresponding to the pronunciation information; The word list, the pronunciation information and the approximate pronunciation information construct a wake-up word recognition network to recognize the voice input by the user according to the wake-up word recognition network, and determine whether to perform a wake-up operation according to the recognition result. The embodiment of the present invention can dynamically construct a wake-up word recognition network for different custom wake-ups, effectively improve the correct rate of wake-ups, reduce false alarm rates, improve wake-up efficiency, occupy less memory, and consume less power.

Description

technical field [0001] The invention relates to the technical field of voice recognition, in particular to an artificial intelligence-based voice wake-up method and device. Background technique [0002] Artificial Intelligence (Artificial Intelligence), the English abbreviation is AI. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. [0003] Voice wake-up technology is an important branch of voice recognition technology. Currently, it has important applications in vehicle, navigation, smart home, etc. It is used ...

AI Technical Summary

Problems solved by technology

[0004] Method 1: When the user defines the wake-up word, the technician redevelops or modifies the wake-up program according to the user-defined wake-up word, and then the user downloads and uses it, which is costly and takes a long time;

[0005] Method 2 directly replaces the wake-up words in the original wake-up network with user-defined wake-up words. However, this method adopts the same recognition strategy for all wake-up words, so there are problems of low wake-up accuracy rate and high false alarm rate.

[0006] The third way is to recognize the voice input by the user through the general voice recognition module to determine whether the voice input by the user contains the wake-up word. However, the general voice recognition model consumes a lot of power and consumes electricity, while the wake-up technology requires real-time monitoring. Therefore, this method will lead to a large power consumption of the device, which is not conducive to the use of localized wake-up technology

Images