A Dual Route Neural Net Approach to Grapheme-to-Phoneme Conversion

Maria Wolters

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

For multilingual text-to-speech synthesis, it is desirable to have reliable grapheme-to-phoneme conversion algorithms which can be easily adapted to different languages. I propose a flexible dual-route neural network algorithm which consists of two components: a constructor net for exploiting regularities of the mapping from graphemes to phonemes and a self-organizing map (SOM) for storing exceptions which are not captured by the constructor net. The SOM transcribes one word at a time, the constructor net one phoneme at a time. The constructor net output is then classified by mapping it onto a set of codebook vectors generated by Learning Vector Quantisation which capture the net's concept of each phoneme.
Original languageEnglish
Title of host publicationArtificial Neural Networks - ICANN 96
Subtitle of host publication1996 International Conference, Bochum, germany, July 16-19, 1996, Proceedings
EditorsChristoph von der Malsburg, Werner von Seelen, Jan C. Vorbrüggen, Bernhard Sendoff
PublisherSpringer Berlin Heidelberg
Number of pages6
ISBN (Electronic)978-3-540-68684-2
ISBN (Print)978-3-540-61510-1
Publication statusPublished - 1996

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin Heidelberg
ISSN (Print)0302-9743


Dive into the research topics of 'A Dual Route Neural Net Approach to Grapheme-to-Phoneme Conversion'. Together they form a unique fingerprint.

Cite this