Voice signal processing method, sound acquisition device and electronic equipment

Abstract

The embodiment of the specification discloses a voice signal processing method, a sound acquisition device and electronic equipment. The scheme is that the voice signal processing method comprises thesteps of: acquiring a first voice signal acquired by a first microphone array and a second voice signal acquired by a second microphone array, wherein the first microphone array and the second microphone array are consistent in target direction, each microphone in the second microphone array is the same in orientation, at least one microphone in the first microphone array is different from the microphones in the second microphone array in orientation; carrying out filtering processing on the first voice signal to obtain a noise reduction gain in the target direction; and according to the noise reduction gain in the target direction, carrying out filtering processing on the second voice signal to obtain an output signal in the target direction.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a voice signal processing method, a voice collection device and electronic equipment. Background technique [0002] In the existing technology, with the rapid development of the Internet of Things technology, voice interaction has become the first choice for the entrance of human-computer interaction due to its convenience in the application fields of smart home, wearable equipment, and intelligent vehicle equipment. Microphone array technology is also Become a very important front-end technology. Especially for some self-service equipment, in the complex acoustic environment of public places, noise and interference always come from all directions. It is very difficult to capture relatively pure speech with a single microphone; the microphone array integrates the space-time information of the speech signal, which can better suppress noise and improve the signal-to-no...

AI Technical Summary

Problems solved by technology

However, a single multi-microphone array often cannot solve all interference problems well. For example, for self-service equipment, the target direction is generally within an angular range directly in front of the screen. Symmetrical interference; although the effect of the ring array to eliminate interference is better, it must be arranged on a cylindrical device. If the thickness of the device is too thin, the ring array cannot be arranged

Images