Wake-up word sound source positioning method and device

Abstract

The embodiment of the invention provides a wake-up word sound source positioning method, a wake-up word sound source positioning device, electronic equipment and a computer readable storage medium. The problem that an existing sound source positioning mode is low in accuracy is solved. The wake-up word sound source positioning method comprises the following steps: acquiring a single-channel wake-up word signal comprising wake-up word voice content; converting the single-channel wake-up word signal into a frequency domain wake-up word signal; based on frequency domain energy values of a plurality of frequency points in a frequency domain corresponding to the frequency domain wake-up word signal, calculating a plurality of weights corresponding to the plurality of frequency points; and obtaining a sound source positioning result based on the plurality of weights corresponding to the plurality of frequency points and the plurality of frequency domain sound signals corresponding to the plurality of microphones.

Description

technical field [0001] The present disclosure relates to the technical field of intelligent interaction, and in particular to a method for locating a sound source of a wake-up word, a device for locating a sound source of a wake-up word, electronic equipment, and a computer-readable storage medium. Background technique [0002] With the continuous development of artificial intelligence technology, human-computer intelligent interaction, as a research hotspot, has been applied in many practical application scenarios. For example, in smart home scenarios, users can save a lot of manual operations by intelligently interacting with smart home devices, thereby improving life experience. Sound wake-up, as an important interaction method of human-computer intelligent interaction, has also been applied in various smart home devices. However, existing smart home devices cannot accurately determine the location of the sound source after being awakened by the sound, which will affect ...

AI Technical Summary

Problems solved by technology

However, existing smart home devices cannot accurately determine the location of the sound source after being awakened by the sound, which will affect the human-computer interaction experience

Especially in a noisy sound environment, if the volume of the interfering sound source is greater than the volume of the wake-up word issued by the user, the smart home device will mistakenly take the direction of the interfering sound source as the direction of the user, thereby reducing the accuracy of sound source localization. Rate

Images