Speech recognition method and speech recognition model training method

The invention relates to a speech recognition and model training method. The training method comprises the following steps: generating a first pronunciation dictionary according to a first phoneme set comprising an adult phoneme set and a child phoneme set; training the first acoustic model by using the training data and the first pronunciation dictionary to obtain the first acoustic model in a first state; performing phoneme and dictionary updating according to the first acoustic model in the first state to obtain a second phoneme set and a second pronunciation dictionary; according to the training data and a second pronunciation dictionary, training the first acoustic model in the first state to obtain a first acoustic model in a second state; generating an initialized second acoustic model according to the first acoustic model in the second state; and training the initialized second acoustic model according to the training data and the second pronunciation dictionary to obtain a second acoustic model. The