A word to phoneme translator

  • Gary Gold
Track 2: Artificial Intelligence
Part of the Lecture Notes in Computer Science book series (LNCS, volume 507)


The problem of translating text to speech is usually approached at the phoneme level using a rule-based system. A rule based system specifies how each letter, or group of letters, will be translated into a basic unit of sound, a phoneme. These rules are very context sensitive, depending on possibly lengthy left and right contexts. The rule based approach in Elovitz [1] and also in Yannakoudakis


Start Condition Rule Base System Input Text Translation Rule Automatic Translation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Honey S. Elovitz, Rodney Johnson, Astrid McHugh, and John E. Shore, Letter-to-sound rules for Automatic Translation of English Text to Phonetics. IEEE Transaction on Acoustics, Speech and Signal Processing, ASSP-24 (1976), 446–459CrossRefGoogle Scholar
  2. [2]
    Dennis H. Klatt, Review of text-to-speech conversion for English, Journal of the Acoustical Society of America, 82 (1987), 737–793CrossRefGoogle Scholar
  3. [3]
    M. E. Lesk and E. Schmidt, Lex — A Lexical Analyzer Generator, in B. W. Kernighan and M. D. McIlroy, UNIX Programmer's Manual, Bell Laboratories, 1978.Google Scholar
  4. [4]
    L. Robert Morris, A Fast FORTRAN Implementation of the U. S. Naval Research Laboratory Algorithm for Automatic Translation of English Text to Votrax Parameters, Proc. Int. Conf. Acoust. Speech Process. ICASSP-79,907–913Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • Gary Gold
    • 1
  1. 1.Department of Computer ScienceWestern Michigan UniversityKalamazooUSA

Personalised recommendations