Neural network control for a cascade/parallel formant synthesizer

Author

Scordilis, Michael S. ; Gowdy, John N.

Author_Institution

Dept. of Electr. & Comput. Eng., Clemson Univ., SC, USA

fYear

1990

fDate

3-6 Apr 1990

Firstpage

297

Abstract

Neural network control of a cascade/parallel formant text-to-speech synthesizer model is investigated. The task under investigation is the synthesis of isolated words spoken in isolation and with neutral intonation. The goals are to have the network successfully learn to produce the temporal parameters that drive the synthesizer and to evaluate its performance on novice utterances. The synthesis strategy and the network architecture and training are discussed, and results for the generation of the fundamental frequency contour using feedforward and sequential networks are shown

Keywords

learning systems; neural nets; speech synthesis; cascade/parallel formant synthesizer; feedforward networks; fundamental frequency contour; isolated words; network architecture; neural network control; neutral intonation; novice utterances; sequential networks; synthesis strategy; temporal parameters; text-to-speech synthesizer model; training; Automatic control; Costs; Frequency synthesizers; Natural languages; Network synthesis; Neural networks; Speech enhancement; Speech synthesis; Synthesizers; User interfaces; Vocabulary;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115639

Filename

115639