3

Looking for pronunciation and syllabification data for American English. I want to analyze pronunciation and spelling rules/heuristics to see how accurate they are and identify exceptions. The goal is to help English as a Second Language students. Rule example: most English words have the accent on the second-to-last syllable.

If it's useful I would make it available to others. No commercial ambitions for now.

The CMU Pronouncing Dictionary (http://www.speech.cs.cmu.edu/cgi-bin/cmudict) has 133K pronunciation entries but without syllabification.

I plan to use data from http://www.wordfrequency.info/ to limit the analysis to the most frequent words (20K? 30K?).

Thanks.

  • What's wrong with wiktionary.org? – Charles Jan 5 '16 at 21:14
  • ... or dictionaryapi.com – Charles Jan 5 '16 at 21:17
  • Not all words in wiktionary.org have pronunciations. Trying less than 10 words, I found that "precision" and "tesseract" don't have pronunciations. dictionary.api.com is a good idea, I'm looking into it. – Jim Fehrle Jan 6 '16 at 3:12

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.