End-to-end speech synthesis training method and system based on knowledge distillation

The invention provides an end-to-end speech synthesis training method and an end-to-end speech synthesis training system based on knowledge distillation. The end-to-end speech synthesis training method comprises the following steps of step 1, acquiring original training data; 2, training a teacher model by using the original training data; 3, training a student model by taking the acoustic characteristic parameters predicted by the teacher model as training data; and 4, performing end-to-end speech synthesis by using the trained student model. According to the method, a knowledge distillationmethod is adopted, a teacher model is trained firstly, then the acoustic characteristic parameters predicted by the teacher model are used as input to train the student model, and finally end-to-end speech synthesis is performed by using the trained student model so that a problem of poor hearing of the out-of-set synthesized speech caused by mismatching of training and testing can be effectivelysolved. 本发明提供了一种基于知识蒸馏的端到端