High Quality Synthetic Speech Generation Using Synchronized Oscillators (Special Section on Speech Synthesis: Current Technologies and Equipment)
スポンサーリンク
概要
- 論文の詳細を見る
For the production of high quality synthetic sounds in a text-to-speech system, an excellent synthesizing method of speech signals is indispensable. In this paper, a new speech analysis-synthesis method for the text-to-speech system is proposed. The signals of voiced speech, which have a line spectrum structure at intervals of pitch in the linear frequency domain, can be represented approximately by the superposition of sinusoidal waves. In our system, anlysis and synthesis are performed using such a harmonic structure of the signals of voiced speech. In the analysis phase, assuming an exact harmonic structure model at intervals of pitch against the fine structure of the short-time power spectrum, the fundamental frequency f_0 is decided so as to minimize the error of the logpower spectrum at each peak position. At the same time, according to the value of the above minimized error, the rate of periodicity of the speech signal is detemined. Then the logpower spectrum envelope is represented by the cosine-series interpolating the data which are sampled at every pitch period. In the synthesis phase, numerical solutions of non-linear differential equations which generate sinusoidal waves are used. For voiced sounds, those equations behave as a group of mutually synchronized oscillators. These sinusoidal waves are superposed so as to reconstruct the line spectrum structure. For voiceless sounds, those non-linear differential equations work as passive filters with input noise sources. Our system has some characteristics as follows. (1) Voiced and voiceless sounds can be treated in a same framowork. (2) Since the phase and the power information of each sinusoidal wave can be easily controlled, if necessary, periodic waveforms in the voiced sounds can be precisely reproduced in the time domain. (3) The fundamental frequency f_0 and phoneme duration can be easily changed without much degradation of original sound quality.
- 社団法人電子情報通信学会の論文
- 1993-11-25
著者
-
Shirai Katsuhiko
The School Of Science And Engineering Waseda University
-
Sato Yasuaki
The School Of Science And Engineering Waseda University
-
Kobayashi Tetsunori
The School Of Science And Engineering Waseda University
-
Hashimoto Kenji
the School of Science and Engineering, Waseda University
-
Mochida Takemi
the School of Science and Engineering, Waseda University
-
Mochida Takemi
The School Of Science And Engineering Waseda University
-
Hashimoto Kenji
The School Of Science And Engineering Waseda University
関連論文
- Genetic Algorithm Based Optimization of Partly-Hidden Markov Model Structure Using Discriminative Criterion(Speech Recognition, Statistical Modeling for Speech Processing)
- High Quality Synthetic Speech Generation Using Synchronized Oscillators (Special Section on Speech Synthesis: Current Technologies and Equipment)