5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

Text-To-Speech Conversion with Neural Networks: A Recurrent TDNN Approach

Orhan Karaali, Gerald Corrigan, Ira Gerson, Noel Massey

Speech Processing Laboratory Motorola, Inc., Schaumburg, IL, USA

This paper describes the design of a neural network that performs the phonetic-to-acoustic mapping in a speech synthesis system. The use of a time-domain neural network architecture limits discontinuities that occur at phone boundaries. Recurrent data input also helps smooth the output parameter tracks. Independent testing has demonstrated that the voice quality produced by this system compares favorably with speech from existing commercial text-to-speech systems.

Full Paper

Bibliographic reference.  Karaali, Orhan / Corrigan, Gerald / Gerson, Ira / Massey, Noel (1997): "Text-to-speech conversion with neural networks: a recurrent TDNN approach", In EUROSPEECH-1997, 561-564.