Voice synthesis method based on voice vector textual characteristics

Abstract

The invention discloses a voice synthesis method based on voice vector textual characteristics. The voice synthesis method comprises the following steps: receiving an input text by a text analyzing module; carrying out regular processing on the textual characteristics and transmitting obtained text data to a text parameterization module; obtaining a parameterized text by adopting a single-bit heat code encoding method; receiving the parameterized text by a voice vector training module, and training a linguistic model based on voice vectors; then transmitting to a linguistic parameter training model to train a mapping model from the text to voice parameters; receiving the output text of the text parameterization module and the voice vector training module through a voice vector generation module, so as to generate the voice vectors of the text data; and transmitting the voice vectors of the text data and the mapping model from the text to the voice parameters to a linguistic parameter predication module to obtain the voice parameters corresponding to the voice vectors; and finally, synthesizing voices by a voice synthesis module. According to the voice synthesis method based on the voice vector textual characteristics, the accuracy of modeling of a voice synthesis system is improved; and the complexity and the manual participation degree of system realization are greatly reduced.

Description

technical field [0001] The invention relates to a speech synthesis method, in particular to a speech synthesis method based on sound vector text features. Background technique [0002] Speech synthesis technology enables computers to generate high-definition, high-naturalness continuous speech, making human-machine communication more harmonious and natural. In the development of speech synthesis technology, the early research mainly used the speech synthesis method based on unit waveform splicing, but this method will cause speech distortion and sudden change at the splicing point. In recent years, the speech synthesis method based on statistical parameters has developed rapidly due to the rapid construction of the synthesis system, small corpus size requirements, and smooth and smooth synthesized speech. However, this method still has the following two shortcomings: [0003] 1. The description of text features is not precise enough, requiring a lot of manpower and material...

AI Technical Summary

Problems solved by technology

[0003] 1. The description of text features is not precise enough, requiring a lot of manpower and material resources to label the text, and a large part of the labeling results depends on the experience and background knowledge of the labelers, which requires professionals to complete, which greatly affects the construction of the system speed;

[0004] 2. There is still a big gap between the sound quality of synthetic speech and real people, especially the speech analysis and synthesis model that uses parametric description of speech and statistical modeling is not ideal, and the modeling of speech is not accurate enough; in addition, the use of statistical parameter modeling , the generated spectral parameter trajectory and fundamental frequency trajectory are too smooth, and the synthetic speech is too flat in the sense of hearing

Images