Voice enhancing method, device, intelligent voice equipment and computer equipment

Abstract

The application provides a voice enhancing method, device, intelligent voice equipment and computer equipment; the method comprises the following steps: obtaining a to-be-processed voice signal; inputting the voice signal into a voice enhancing model, removing noises and / or interference voices in the voice signal so as to obtain a processed voice signal; the voice enhancing model is obtained by training mixed voice signals; the mixed voice signals refer to signals obtained by adding noises and / or interference voices in pure wakeup word voice signals; the pure wakeup word voice signals refer towakeup word voice signals with a noise and / or interference voice ratio smaller than a proportion threshold; the voice enhancing model can effectively remove noises and / or interference voices from thevoice signal, such as voices related to non-wakeup words, thus improving the voice enhancing effect; the method and device can carry out voice identification treatment for the processed voice signal,thus improving wakeup word identification accuracy and wake up efficiency, and improving the user usage experiences.

Description

technical field [0001] The present application relates to the technical field of voice processing, in particular to a voice enhancement method, device, intelligent voice equipment and computer equipment. Background technique [0002] The current speech enhancement method is to use a deep learning model to perform blind source separation on the speech signal to be processed, and obtain the signals of each speaker in the speech signal; in the signal of each speaker, the voices of other speakers are suppressed; and then The individual speaker signals are used for speech recognition. However, in the above scheme, since the characteristics of different speech contents of different people are different, it is difficult to distinguish the characteristics of different speech contents of different people, resulting in the separated signals of each speaker being mixed with the voices of other speakers, which makes it difficult to accurately The recognition of the wake-up word reduces...

AI Technical Summary

Problems solved by technology

However, in the above scheme, since the characteristics of different speech contents of different people are different, it is difficult to distinguish the characteristics of different speech contents of different people, resulting in the separated signals of each speaker being mixed with the voices of other speakers, which makes it difficult to accurately Recognize the wake-up word, which reduces the accuracy of wake-up word recognition and wake-up efficiency

Images