Method, device and system for solving pulse signal generated at splicing position in speech synthesis

Abstract

The invention provides a method, a device and a system for solving a pulse signal generated at a splicing position in speech synthesis, and the method comprises the following steps: extracting two speech segments to be spliced from a database as a first speech segment and a second speech segment respectively, and reserving N sampling points from the first speech segment and the second speech segment as overlapping parts, wherein N is greater than 256; calculating a gradual-out coefficient vector and a gradual-in coefficient vector according to the sampling points; utilizing the gradual-out coefficient vector and the gradual-in coefficient vector to obtain a sampling point value of an overlapped part; and completing splicing of the first speech segment and the second speech segment based onthe obtained sampling point values of the overlapped parts. According to the method, the original reason of the pulse signal generated at the splicing position during speech synthesis is not concerned, the speech smoothing effect is achieved through weighted average of the sampling point values of the front segment and the rear segment, the negative influence of the pulse signal on the overall rhythm, tone quality and listening feeling of speech is greatly improved, and the noise phenomenon can be reduced or avoided.

Description

technical field [0001] One or more embodiments of the present invention relate to the technical field of natural language processing, and in particular to a method, device and system for solving pulse signals generated at splicing points in speech synthesis. Background technique [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein may include concepts that could be explored, but not necessarily concepts that have been previously thought of or explored. Therefore, unless otherwise indicated herein, what is described in this section is not prior art to the description and claims in this application and is not admitted to be prior art by inclusion in this section. [0003] With the rapid development of intelligent voice technology, voice interaction has become a necessary solution for human-computer interaction in many smart devices. For example, more and more enterpris...

AI Technical Summary

Problems solved by technology

[0007] One or more embodiments of this specification describe a method, device and system for solving the pulse signal generated at the splicing point in the speech synthesis, which can solve the problem in the current technology that the pulse signal is often generated at the splicing point of two speeches during the speech synthesis process. , prone to noise problems

Images