Hello, I have been using CMU Sphinx to do audio-text alignment in Dutch. There are quite a lot of words in my grammar files that are out of vocabulary. For these words, I obtained the IPA transcriptions using eSpeak. Is there a script or a tool that I can use to convert IPA to ARPABET phonemes? I am not a native speaker of Dutch; hence, I do not prefer writing the mapping myself. In general, is there an automatized way to obtain ARPABET transcriptions of a given Dutch word (without IPA)?
Best.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello, I have been using CMU Sphinx to do audio-text alignment in Dutch. There are quite a lot of words in my grammar files that are out of vocabulary. For these words, I obtained the IPA transcriptions using eSpeak. Is there a script or a tool that I can use to convert IPA to ARPABET phonemes? I am not a native speaker of Dutch; hence, I do not prefer writing the mapping myself. In general, is there an automatized way to obtain ARPABET transcriptions of a given Dutch word (without IPA)?
Best.
--- Try the attached mapping, See if it is useful.
is there an automatized way to obtain ARPABET transcriptions of a given Dutch word (without IPA)
-- You can try Phonetisaurus with Dutch G2P model.
Last edit: G10DRAS 2019-05-04