Training method and training device for acoustic model and storage medium

The invention provides a training method and a training device for an acoustic model and a storage medium. The method comprises the following steps: training an initial model by adopting Chinese voicedata to obtain a first neural network; obtaining a second neural network according to the first neural network, wherein an output layer of the second neural network comprises N+S nodes, N nodes correspond to N types of the Chinese voice data and S nodes correspond to S types of the Chinese voice data; and training the second neutral network by adopting the Chinese voice data and English voice data to obtain the acoustic model. According to the training method and the training device for the acoustic model and the storage medium, the trained acoustic model applied to Chinese and English mixedvoice data recognition can improve the recognition rate of Chinese voice data. 本发明提供种声学模型的训练方法、装置及存储介质，其中方法包括：采用中文语音数据训练初始模型得到第神经网络；根据第神经网络得到第二神经网络；其中，第二神经网络的输出层包含N+S个节点，N个节点对应中文语音数据的N个类别，S个节点对应英文语音数据的S个类别；采用中文语音数据和英文语音数据对第二神经