METHOD AND APPARATUS FOR TRAINING MODEL, METHOD AND APPARATUS FOR SYNTHESIZING SPEECH, DEVICE, STORAGE MEDIUM AND COMPUTER PROGRAM PRODUCT

The present disclosure discloses a method and apparatus for training a model, a method and apparatus for synthesizing a speech, a device, a storage medium and a computer program product, and relates to the field of natural language processing and deep learning technology. At a training stage of a model, an implementation specifically includes: determining a phoneme feature and a prosodic word boundary feature of sample text data; inserting a pause character into the phoneme feature according to the prosodic word boundary feature to obtain a combined feature of the sample text data; and training an initial speech synthesis model according to the combined feature of the sample text data, to obtain a target speech synthesis model. According to the technique in the present disclosure, the fluency of the speech synthesis is improved.