Training method and apparatus of text regularization model anda text regularization method and apparatus

Abstract

The application discloses a training method and apparatus of a text regularization model and a text regularization method and apparatus. According to one embodiment, the training method includes: characters in an input character sequence corresponding to an input text are inputted into a neural network corresponding to a to-be-generated text regularization model, wherein the neural network corresponding to the text regularization model includes a coder and a decoder; for each character in the input character sequence, coding is carried out by the coder based on a state after decoding of a previous inputted character by a hidden layer in the decoder, so that an intermediate semantic vector of the character is obtained, and the intermediate semantic vector is interpreted by using the decoderto obtain a prediction result of the character; and according to a difference between the prediction result of the input character sequence and a marking result corresponding to the input text, the parameter of the neural network is adjusted. Therefore, automatic training of the text regularization model is realized and flexibility and accuracy of the text regularization model are improved.

Description

technical field [0001] The present application relates to the field of computer technology, specifically to the field of speech synthesis technology, and in particular to a text regularization model training method and device, and a text regularization method and device. Background technique [0002] Artificial Intelligence (AI) is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that responds in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, speech synthesis, Image recognition, natural language processing and expert systems, etc. Among them, speech synthesis technology is an important direction in the field of computer science and artificial intelligence. ...

AI Technical Summary

Problems solved by technology

However, the generalization of the rule-based method is poor, and there are strict restrictions on the context of the text. If the text format or content changes slightly, the corresponding rules may become invalid.

And with the increase of TTS requests, the diversity of each text changes, the number of rules gradually increases, and the maintenance of rules becomes more and more difficult, which is not conducive to saving resources

Images