SPEECH RECOGNITION METHOD AND APPARATUS

The present application relates to a speech recognition method and apparatus. The speech recognition method comprises: a terminal device inputting a phoneme to be recognized into a first multi-task neural network model; the first multi-task neural network model outputting a first prediction result, wherein the first prediction result comprises a character prediction result and a punctuation prediction result, which correspond to said phoneme; and the terminal device displaying at least part of the first prediction result on a display screen of the terminal device. By means of constructing a neural network model for simultaneously predicting a character and punctuation corresponding to a phoneme, the character and punctuation corresponding to the phoneme can be simultaneously output, and the neural network model has a small size and can thus be deployed at an end side. La présente demande concerne un procédé et un appareil de reconnaissance vocale. Le procédé de reconnaissance vocale comprend les étapes suivan