Speech processing method, speech encoder, speech decoder and speech recognition system

Abstract

A speech processing method, a speech encoder, a speech decoder, and a speech recognition system are provided. The method includes: obtaining a speech signal to be processed; using a first neural network and a second neural network to process the speech signal to obtain first feature information and second feature information corresponding to the speech signal respectively, wherein a computational efficiency of the first neural network is higher than a computational efficiency of the second neural network, and an accuracy of the second feature information outputted by the second neural network is higher than an accuracy of the first feature information outputted by the first neural network; and determining target feature information used to represent semantics in the speech signal based on the first feature information and the second feature information.