Speech synthesizer and method for synthesizing speech for superposing and adding a waveform onto a waveform obtained by delaying a previously obtained waveform
First Claim
1. A speech synthesizer comprising:
- first indication means for indicating the amplitude of a waveform by using a random number;
second indication means for indicating the superposition period for waveforms by using a random number;
waveform generating means for generating a waveform having an amplitude indicated by said first indication means;
waveform superposition means for superposing and adding the waveform generated by said waveform generating means onto a waveform obtained by delaying the waveform, which is previously generated by said waveform generating means, by a superposition period indicated by said second indication means; and
output means for outputting the waveform added by said waveform superposition means as unvoiced speech.
0 Assignments
0 Petitions
Accused Products
Abstract
A speech synthesizer includes a first indicator for indicating the amplitude of a waveform by using a random number, a second indicator for indicating the superposition period for waveforms by using a random number, a waveform generator for generating first and second waveforms having an amplitude indicated by the first indicator, and a waveform superposition device for synthesizing an unvoiced speech waveform by superposing the second waveform generated by the waveform generator onto a waveform obtained by delaying the first waveform by a superposition period indicated by the second indication means. The speech synthesizer is capable of making the frequency characteristic of unvoiced speech analogous to that of white noise, and generating synthesized speech which is natural and analogous to an actual human voice.
-
Citations
12 Claims
-
1. A speech synthesizer comprising:
-
first indication means for indicating the amplitude of a waveform by using a random number; second indication means for indicating the superposition period for waveforms by using a random number; waveform generating means for generating a waveform having an amplitude indicated by said first indication means; waveform superposition means for superposing and adding the waveform generated by said waveform generating means onto a waveform obtained by delaying the waveform, which is previously generated by said waveform generating means, by a superposition period indicated by said second indication means; and output means for outputting the waveform added by said waveform superposition means as unvoiced speech. - View Dependent Claims (2, 3)
-
-
4. A speech synthesizer comprising:
-
indication means for indicating the superposition period of waveforms by using a random number; waveform superposition means for synthesizing an unvoiced speech waveform by superposing and adding a second waveform onto a waveform obtained by delaying a first waveform by said superposition period indicated by said indication means; and output means for outputting the waveform added by said waveform superposition means as unvoiced speech. - View Dependent Claims (5, 6)
-
-
7. A method for synthesizing speech, comprising the steps of:
-
indicating the amplitude of a waveform by using a random number; indicating the superposition period for waveforms by using a random number; generating a waveform having an amplitude indicated by said amplitude indicating step; superposing and adding the waveform generated in said generating step onto a waveform obtained by delaying the waveform, which is previously generated in said waveform generating step, by a superposition period indicated in said indicating step; and outputting the waveform added in said superposing and adding step as unvoiced speech. - View Dependent Claims (8, 9)
-
-
10. A method for synthesizing speech, comprising the steps of:
-
indicating the superposing period of a waveform by using a random number; synthesizing an unvoiced speech waveform by superposing and adding a second waveform onto a waveform obtained by delaying a first waveform by the superposition period indicated in said indicating step; and outputting the waveform added in said superposing and adding step as unvoiced speech. - View Dependent Claims (11, 12)
-
Specification