Suzhou Keda Technology Co., Ltd.

Renxiang Yan

Lijun Cao

Hongjie Pu

Sainan Zhu

Provided is a voice signal processing method. The method comprises the following steps: acquiring a status coefficient, a target voice signal to be processed, and a derivative signal of the target voice signal (S); using the derivative signal to respectively calculate an initial echo loss corresponding to each signal frame in the target voice signal, then using the status coefficient to adjust the initial echo loss to acquire a target echo loss (S); using the derivative signal to calculate a proximal-distal coherence value of the target voice signal (S); judging whether the target echo loss matches with a single-talk echo state (S); if so, recording the proximal-distal coherence value in the status statistical data, and updating statistical information (S); and using the statistical information to update the status coefficient, and performing volume control on the target voice signal after the status coefficient is updated (S). The method ensures better sound quality, and further improves user experience. Also provided are a voice signal processing device, an apparatus, and a readable storage medium, having corresponding technical effects.

Growing community of inventors

Suzhou, China

Renxiang Yan