Zhejiang Lab

Zhenchuan Zhang

Jingsong Li

Yu Tian

Tianshu Zhou

The present disclosure discloses a general speech enhancement method and apparatus using multi-source auxiliary information. The method includes following steps: S: building a training data set; S: using the training data set to learn network parameters of a model, and building a speech enhancement model; S: building a sound source information database in a pre-collection or on-site collection mode; S: acquiring an input of the speech enhancement model; and S: taking a noisy original signal as a main input of the speech enhancement model, taking auxiliary sound signals of a target source group and auxiliary sound signals of an interference source group as side inputs of the speech enhancement model for speech enhancement, and obtaining an enhanced speech signal.

Growing community of inventors

Hangzhou, China

Zhenchuan Zhang