Sound source positioning method and device and air conditioner

Abstract

The invention discloses a sound source positioning method and device, and the method comprises the steps: obtaining an audio signal received by a microphone array, wherein the microphone array comprises a plurality of microphones; obtaining the relative time difference between the audio signal received by any two of the plurality of microphones according to the audio signals and a preset parameter, wherein the preset parameter is set according to the SNR (signal to noise ratio); and carrying out the positioning of the audio signal according to the relative time difference between the audio signal received by any two of the plurality of microphones and the position of each microphone. The method can effectively and adaptively reduce the environment noise, has the strong capability of adapting to and resisting the reverberation and diffraction noise in a far-field environment, improves the recognition precision of a far-field sound source based on the microphone array, and improves the recognition practicality of the far-field sound source. The invention also proposes an air conditioner, a non-temporary computer readable storage medium, and a computer program product.

Description

technical field [0001] The present invention relates to the field of sound source localization, in particular to a sound source localization method, a sound source localization device, an air conditioner, a non-transitory computer-readable storage medium and a computer program product. Background technique [0002] Home appliances such as air conditioners and electric fans have become indispensable products in people's lives. With the rapid development of artificial intelligence technology, home appliances with voice recognition functions are emerging in an endless stream, which greatly improves people's experience in using home appliances. . Speech recognition technology relies on voice pickup, and the core component of voice pickup is a microphone, that is, the voice input is obtained through a microphone array. However, the microphone array not only picks up the voice signal, but also simultaneously picks up various noises mixed in the voice signal. Before voice recognit...

AI Technical Summary

Problems solved by technology

[0004] However, although the algorithm principle in the above technology is simple, the error is large

The actual home appliance use environment is mostly a far-field sound recognition environment, and there are often large environmental noises and strong reverberations. The FIR bandpass filter cannot filter out most of the background noise mixed in the sound source, and the indoor The processing ability of reverberation and sound diffraction is weak, which seriously affects the identification effect of sound source

Images