Speech synthesis method and system

Abstract

The invention discloses a speech synthesis method and system. The method includes steps: receiving a to-be-synthesized text; pre-processing the to-be-synthesized text to obtain a to-be-synthesized unit sequence of the to-be-synthesized text and context related information of to-be-synthesized units\; obtaining optimal alternative speech data of the to-be-synthesized unit sequence from a speech database according to the context related information of the to-be-synthesized units; obtaining a monitoring result of the alternative speech data from monitoring personnel; expanding the speech database according to the monitoring result; obtaining the optimal alternative speech data of the to-be-synthesized unit sequence, which is regarded as optimized speech data, again by employing the expanded speech database; and outputting the synthesis speech data of the to-be-synthesized text which is the optimized speech data. By employing the method and system, artificial subjective hearing feelings can be accurately combined to a synthesis result of the to-be-synthesized text, and the speech synthesis effect is improved.

Description

technical field [0001] The invention relates to the technical field of speech synthesis, in particular to a speech synthesis method and system. Background technique [0002] It has become an urgent need for the application and development of information technology to realize humanized and intelligent effective interaction between man and machine, and to build an efficient and natural human-machine communication environment. As an important part of human-computer communication, speech synthesis technology can convert text information into natural speech signals, endow computers with the ability to speak freely like humans, and change the traditional cumbersome operation of realizing machines to speak through recording and playback. In order to make the synthesized speech more natural and more in line with human subjective hearing, a speech synthesis method that integrates human subjective listening has emerged. The specific fusion method is generally to analyze the artificial...

AI Technical Summary

Problems solved by technology

However, when the existing synthesis system synthesizes speech, the number of incorrectly synthesized speech units is far less than the number of correctly synthesized speech units, that is, the distribution of the two types of training data for training the classification model is unbalanced, which leads to the training of the classification model. The wrong synthetic unit tends to be the correct synthetic unit, which affects the selection of the optimal synthetic result of the text to be synthesized

Images