A neural network model for Chinese speech synthesis

Author

Xiang, Zengjun ; Bi, Guangguo

Author_Institution

Dept. of Radio Eng., Southeast Univ., Nanjing, China

fYear

1990

fDate

1-3 May 1990

Firstpage

1859

Abstract

A multilayer back-propagation neural-network model which performs Chinese speech synthesis with high speed quality is described. The following are detailed: (1) the basic properties of the neural network and its difference from the traditional methods for speech processing; (2) selection of basic acoustic units which can be concatenated to generate utterances; (3) selection of the formant parameters; and (4) hybrid formant synthesizer and its neural network architecture. The test written in Chinese phonetic symbols (Chinese pingyin) is conveyed into the system and the speech with unlimited vocabulary is produced by the rules

Keywords

neural nets; speech analysis and processing; speech synthesis; Chinese phonetic symbols; Chinese pingyin; Chinese speech synthesis; acoustic units; formant parameters; hybrid formant synthesizer; multilayer back-propagation; neural network model; speech processing; speed quality; utterances; Acoustic testing; Concatenated codes; Hybrid power systems; Multi-layer neural network; Neural networks; Speech processing; Speech synthesis; Synthesizers; System testing; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1990., IEEE International Symposium on

Conference_Location

New Orleans, LA

Type

conf

DOI

10.1109/ISCAS.1990.112027

Filename

112027