Speech recognition method and device, computer equipment and storage medium

The invention provides a voice recognition method and device, computer equipment and a storage medium. The method comprises the steps: acquiring a word graph obtained by performing preliminary decoding on a to-be-identified audio; acquiring scene corpus data under a target business scene to which the audio belongs; training an N-element grammar language model according to the scene corpus data, and reordering the word graph by using the N-element grammar language model; inputting the word sequence on each path in the reordered word graph into a pre-trained neural network language model to reorder the reordered word graph again through the neural network language model so as to correct the probability corresponding to each edge after reordering, wherein the neural network language model is obtained by training first original corpus data of different scenes; and outputting a voice recognition result for the audio according to the reordered word graph. According to the scheme, the speech recognition accuracy can