Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Self-Organizing Letter Code-Book for Text-To-Phoneme Neural Network Model

Kare Jean Jensen, Søren Riis

Nokia Mobile Phones, Frederikskaj, Denmark

This paper describes an improved input coding method for a textto- phoneme (TTP) neural network model for speaker independent speech recognition systems. The code-book is self-organizing and is jointly optimized with the TTP model ensuring that the coding is optimal in terms of overall performance. The codebook is based on a set of single layer neural networks with shared weights. Experiments show that performance is increased compared to the NETTalk and NETSpeak models.


Full Paper

Bibliographic reference.  Jensen, Kare Jean / Riis, Søren (2000): "Self-organizing letter code-book for text-to-phoneme neural network model", In ICSLP-2000, vol.3, 318-321.