Speech synthesis method, system and mobile terminal equipment with speech synthesis function

Abstract

The invention provides a speech synthesis method, a speech synthesis system and mobile terminal equipment with a speech synthesis function, which solve the problem of the huge computation amount of the conventional real-time synthesis. The method comprises the following steps of: regulating speech parameters of a sample in a model training state and then counting and training the regulated parameters to obtain a parameter model; and in a speech synthesis stage, performing speech parameter planning on information to be synthesized by using the parameter model, and then planning parameter synthesized speeches. In the method, the regulation process of the speech parameters is transferred to the model training stage to be finished and is not performed any more in the real-time synthesis, which reduces the computation amount of the real-time synthesis and ensures the real-time property of the speech synthesis. In addition, the invention also provides the mobile terminal equipment with the speech synthesis function, which can reduce the computation amount of the real-time synthesis.

Description

technical field [0001] The present invention relates to the technical field of signal processing, in particular to a speech synthesis method and system, and a mobile terminal device with a speech synthesis function. Background technique [0002] The speech generated by humans through certain machine equipment is called speech synthesis (Speech Synthesis). In terms of technology, speech synthesis can be divided into waveform splicing synthesis, parameter analysis synthesis, etc. [0003] Among them, the parametric analysis synthesis method mostly uses syllables, semi-syllables or phonemes as the synthesis unit. First, according to the theory of speech, extract relevant speech parameters from the speech of all synthesis units, and then conduct statistical analysis to generate a parameter model library; when synthesizing, plan the corresponding synthesis parameters from the parameter model library according to the text information to be synthesized, Then it is sent to a speec...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to provide a speech synthesis method and system to solve the problem of large amount of calculation in the existing real-time synthesis

Images