Text conversion model training method and device, text conversion method and device

Abstract

The application discloses a text conversion model training method and device, and a text conversion method and device. A specific embodiment of the text conversion model training method includes: sequentially inputting the characters in the input character sequence corresponding to the input text into the neural network corresponding to the text conversion model to be generated, and the neural network corresponding to the text conversion model includes an encoder and a decoder. For each character in the input character sequence, based on the state of the hidden layer in the decoder after decoding the last character input, the encoder is used to encode to obtain the intermediate semantic vector of the character, and the intermediate semantic vector is obtained by the decoder. The semantic vector is interpreted to obtain the prediction result of the character; according to the difference between the prediction result of the input character sequence and the labeling result corresponding to the input text, the parameters of the neural network are adjusted. The text conversion model obtained in this implementation manner can realize text regularization and joint prediction of polyphonic characters, reducing resource maintenance costs.

Description

technical field [0001] The embodiments of the present application relate to the field of computer technology, specifically to the field of speech synthesis technology, and in particular to a text conversion model training method and device, and a text conversion 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 intel...

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.

Moreover, there is overlap between the resources required for text regularization processing and the resources required for polyphonic pronunciation annotation (such as the corpus required for building rules), and the maintenance cost of these resources is relatively high

Images