Speech synthesis method, system, device and storage medium

A speech synthesis and audio technology, applied in the computer field, can solve the problems of inaccurate response to text expression, low audio accuracy, and long time, so as to avoid the risk of missing words, increase the speed, and reduce the possibility of missing words Effect
CN112786000BActive Publication Date: 2022-06-03亿度慧达教育科技(北京)有限公司
6 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
亿度慧达教育科技(北京)有限公司
Publication Date
2022-06-03

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

Embodiments of the present invention provide a speech synthesis method, system, device, and storage medium. The method includes: obtaining text to be speech synthesized; obtaining each text unit matrix according to the text; obtaining each of the text unit matrices according to the pre-stored text unit spectrum sequence. The unit spectrum matrix corresponding to the text unit matrix, and the number of unit spectrum frames corresponding to each of the text unit matrices is obtained, wherein the text unit spectrum sequence stores the text unit matrix and the unit spectrum matrix corresponding to each other Constructing a text spectrum matrix corresponding to the text according to the number of unit spectrum frames and the unit spectrum matrix; performing speech synthesis on the text spectrum matrix to obtain audio corresponding to the text. The speech synthesis method, system, device and storage medium provided by the embodiments of the present invention can obtain accurate speech synthesis audio within a relatively short speech synthesis time.
Need to check novelty before this filing date? Find Prior Art

Description

Speech synthesis method, system, device and storage medium technical field Embodiments of the present invention relate to the field of computers, and in particular to a method, system, device and storage medium for speech synthesis quality. Background technique

[0002] Speech synthesis (text to speech, TTS) technology is a speech technology that converts text into audio. In recent years, along with the development of speech technology, speech synthesis technology has wide application in many fields, such as: Audio reading, smart speakers, simultaneous transmission and other fields. However, the current speech synthesis method, or the time required for audio generation, or the resulting speech Synthesized audio has low accuracy and cannot accurately reflect the expression of the text. Therefore, how to obtain accurate speech synthesis audio in a shorter speech synthesis time becomes an urgent need to solve technical issues. SUMMARY OF THE INVENTION The techni...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More