Beijing Xiaomi Mobile Software Co., Ltd.

Haojun Ai

Fei Xiang

Linjun Cai

Shicong Li

Jiaqian Feng

Yuhong Yang

Weiping Tu

A method for evaluating performance of a speech enhancement algorithm includes: acquiring a first speech signal including noise and a second speech signal including noise, wherein the first speech signal is acquired from a near-end audio acquisition device close to a sound source, the second speech signal is acquired from a far-end audio acquisition device far from the sound source, and the near-end audio acquisition device is closer to the sound source than the far-end audio acquisition device; acquiring a pseudo-pure speech signal based on the first speech signal and the second speech signal, as a reference speech signal; enhancing the second speech signal by using a preset speech enhancement algorithm, to obtain a denoised speech signal to be tested; and acquiring a correlation coefficient between the reference speech signal and the speech signal to be tested, for evaluating the speech enhancement algorithm.

Growing community of inventors

Beijing, China

Haojun Ai