Title :
Automatic demi-syllable extraction for speech synthesis utilising artificial neural networks
Author :
Jennings, D.T. ; Westaway, L. ; Curtis, K.M.
Author_Institution :
Dept. of Electr. & Electron. Eng., Nottingham Univ., UK
Abstract :
A method for automatically recognising and extracting all the demi-syllable speech units for synthesis within a text to speech system is presented, the method utilises artificial neural networks enabling speaker independent demi-syllable recognition. The units are automatically stored in a directory tree for use in the University of Nottingham´s analysis/synthesis text to speech system
Keywords :
backpropagation; feature extraction; multilayer perceptrons; speaker recognition; speech synthesis; University of Nottingham; artificial neural networks; automatic demi-syllable extraction; backpropagation; directory tree; multilayer perceptron; speaker independent demi-syllable recognition; speech analysis; speech synthesis; text to speech system; Artificial neural networks; Autocorrelation; Data mining; Databases; Dictionaries; Finite impulse response filter; Intrusion detection; Natural languages; Parameter extraction; Speech synthesis;
Conference_Titel :
Digital Signal Processing Proceedings, 1997. DSP 97., 1997 13th International Conference on
Conference_Location :
Santorini
Print_ISBN :
0-7803-4137-6
DOI :
10.1109/ICDSP.1997.628415
