Sound source positioning method, device and electronic apparatus

Abstract

The embodiments of the invention disclose a sound source positioning method, a sound source positioning device and an electronic apparatus. The method includes the following steps that: when being in a sleep state, the electronic apparatus continuously receives speech signals; whether an interaction instruction corresponding to each of the received speech signals is a wake-up instruction is judged; if the interaction instruction is not a wake-up instruction, the sound source direction of the speech signal is recorded and is adopted as a first type sound source direction; if the interaction instruction is a wake-up instruction, the electronic apparatus is switched from the sleep state to a work state, and the sound source direction of the speech signal is positioned and recorded, and is adopted as a second type sound source direction; and the sound source direction of a user is positioned according to the first type sound source direction and the second type sound source direction. According to the sound source positioning method, the sound source positioning device and the electronic apparatus provided by the embodiments of the invention, the sound source direction of the user is positioned according to the first type sound direction of the speech signal received under the sleep state and the second type sound source direction of the speech signal received under the work state, and therefore, the accuracy of the sound source positioning of the user is greatly improved, and user experience is better.

Description

technical field [0001] The invention relates to the technical field of voice signal processing, in particular to a sound source localization method, device and electronic equipment. Background technique [0002] At present, there are more and more products on the market with voice interaction functions, such as electronic devices such as smart speakers and robots. When these electronic devices receive a wake-up command, they will turn from a sleep state to a working state, and start to receive voice signals through the microphone array, and then can recognize and analyze the voice signals, thereby responding to the interactive commands corresponding to the voice signals. Obviously, in the process of product function realization, sound source localization is very important. Only by accurately locating the direction of the user's sound source can the voice signal sent by the user be accurately obtained and the correct response behavior can be performed. [0003] After receivi...

AI Technical Summary

Problems solved by technology

[0004] This sound source localization method can accurately locate the direction of the user's sound source in a quiet environment, but in a noisy environment, there are multiple sound sources, and the volume of the noise source may be large, and electronic equipment will mistakenly detect the user's sound source. The sound source location of the noise is identified as the location of the user's sound source, and the noise is recognized as the voice signal sent by the user, and a wrong response is made. The accuracy of the user's sound source location is very low, and the user experience is not good.

Images