Deep Learning-based Chinese Speech Recognition in Food Safety Field

In order to solve the problems of poor robustness of speech recognition and inaccurate recognition of proper nouns in the field of food safety, this paper creates a Chinese speech recognition model, constructs an acoustic model using Deep Full Sequence Convolutional Neural Network (DFCNN) and Connectionist Temporal Classification (CTC), constructs an acoustic model of A language model is constructed based on statistics, and a terminology database is constructed based on the collation of scientific knowledge in the field of food safety. The speech recognition method achieved a correct rate of89.8% on the optimal model and was able to effectively recognize proper nouns in the field of food safety.