Speech sunthetic device and method

Abstract

A speech synthesis apparatus (10) comprises speech segment disassembling means (101) for disassembling the speech segments each including at least one phoneme into a plurality of pitch waveforms, phase characteristic transforming means (103) for transforming the phase characteristics of the pitch waveforms into a uniformed phase characteristic, pitch waveform classifying means (104) for classifying the pitch waveforms into a plurality of groups, pitch waveform registering means (106) for registering the pitch waveforms in the database (111) by extracting one pitch waveform from among the pitch waveforms in each of the groups, and synthesizing means (107) for synthesizing the speech with the pitch waveforms registered in the database (111). The speech synthesis apparatus (10) thus constructed can synthesize a natural speech using a relatively small database capacity.

Description

technical field [0001] The present invention relates to a kind of speech synthesis device and speech synthesis method, be used for synthesizing the speech that is made up of a plurality of speech segments (speech segment), each speech segment comprises at least one phoneme; Particularly relate to such a kind of speech synthesis device and speech synthesis method that can synthesize natural speech with a relatively small database size. Background technique [0002] In conventional speech synthesis devices and speech synthesis methods, the speech in some languages ​​is usually divided into a plurality of speech segments, and each speech segment contains at least one phoneme in the language. Furthermore, each speech segment is usually decomposed into multiple pitch waveforms. Each pitch waveform obtained by decomposing each speech segment is associated with each speech segment and recorded in the database. The pitch waveforms in the database are us...

AI Technical Summary

Problems solved by technology

[0004] However, the above-mentioned conventional speech synthesis method suffers from a problem that the database cannot record pitch waveforms with significantly reduced data because, before synthesizing natural speech, the pitch waveform shapes vary due to their different phase characteristics.

Another problem is that, in order to save the capacity of the database, only a small number of pitch waveforms are recorded in this database, resulting in lower sound quality of synthesized speech

Images