Awakening performance optimization method and system based on mode switching

Abstract

The invention discloses an awakening performance optimization method and system based on mode switching. The method comprises the steps: acquiring awakening words; setting awakening modes, including asecondary awakening mode, a deep sleep mode and a common awakening mod, of to-be-awakened equipment according to an application scene; determining a secondary threshold value corresponding to the secondary awakening mode, a sleep threshold value corresponding to the deep sleep mode and a standard threshold value corresponding to a common awakening mode; and controlling the to-be-awakened equipment to switch among the three modes according to the awakening word, the secondary threshold, the sleep threshold and the standard threshold. Compared with a single common awakening mode, the awakeningperformance optimization method and system disclosed by the invention have the advantages that the secondary awakening mode is added, so that the awakening rate is improved; the deep sleep mode is added, so that the false awakening rate is reduced, and increasingly stringent performance indexes of a user can be met.

Description

technical field [0001] The present invention relates to the technical field of speech recognition, in particular to a method and system for optimizing wake-up performance based on mode switching. Background technique [0002] Wake-up rate and false wake-up rate are two important indicators of speech recognition products, both of which are directly related to the "awakening threshold". The usual implementation is to select a fixed reference arousal threshold according to the experimental results for a specific wake-up word. Based on this threshold, the recognition result of the device to be woken up is classified as follows: if the confidence of the recognition result is greater than the threshold, it is considered to be a valid wake-up; otherwise, it is considered to be an invalid wake-up. [0003] At present, the method of judging effective wake-up and invalid wake-up completely relies on a single reference threshold obtained from experiments at the algorithm level, and th...

AI Technical Summary

Problems solved by technology

[0003] At present, the way of distinguishing effective wake-up and invalid wake-up depends entirely on a single reference threshold obtained from experiments based on the algorithm level, and there is only a common wake-up mode corresponding to this reference threshold. If the single reference threshold is selected too large, it will lead to a higher wake-up rate. On the contrary, if it is too small, it will lead to increased false wake-ups, which cannot meet the increasingly stringent performance indicators of users.

Images