Voice synthetic method, voice synthetic device and recording medium

Abstract

A speech synthesis method comprises selecting a predetermined formant parameters from formant parameters according to a pitch pattern, phoneme duration, and phoneme symbol string, generating a plurality of sine waves based on formant frequency and formant phase of the formant parameters selected, multiplying the sine waves by windowing functions of the selected formant parameters, respectively, to generate a plurality of formant waveforms, adding the formant waveforms to generate a plurality of pitch waveforms, and superposing the pitch waveforms according to a pitch period to generate a speech signal.

Description

[0001] Cross References to Related Applications [0002] This application is based on and claims priority from the prior Japanese Patent Application No. 2001-08704 filed on March 26, 2001, the entire contents of which are incorporated herein by reference. technical field [0003] The invention relates to text-to-speech synthesis, in particular to the speech synthesis to generate speech signals from information such as phoneme symbol strings, pitches, and phoneme durations. Background technique [0004] Making speech signals from arbitrary texts is called text-to-speech synthesis. Usually, this text-to-speech synthesis system includes three stages: a speech processing unit, a phoneme processing unit, and a speech signal generation unit. [0005] The input text is first subjected to morphological analysis and composition analysis in the speech processing unit, and then the stress and intonation are processed in the phoneme processing unit, and the phoneme symbol string, pitch...

AI Technical Summary

Problems solved by technology

However, there is the problem of poor model accuracy

That is to say, only using the formant frequency and frequency bandwidth cannot express the fine structure of the spectrum of the actual speech, and the sound quality is poor and lacks the sense of human voice (human-like degree)

Images