Speech recognition method and device, server and computer readable storage medium

The invention relates to a speech recognition method and device, a server and a computer readable storage medium. The speech recognition method comprises the steps of: performing acoustic feature extraction on speech data to be processed, inputting extracted acoustic features into an acoustic model, and calculating acoustic model scores of the acoustic features; and decoding the acoustic features and the acoustic model scores of the acoustic features by adopting a main decoding network and a sub-decoding network to obtain a speech recognition result. According to the speech recognition method, the decoding network of a scene to be recognized is not retrained, instead, a target named entity in the scene to be recognized is trained to obtain a sub-decoding graph, and then the main decoding network and the sub-decoding network are used for decoding to obtain the speech recognition result. Therefore, for the target named entity in the scene to be recognized, the target named entity can be accurately decoded based