10

I'm searching for a tool that converts text to phonemes, (like text to speech software) I can program one but it will not be without errors and takes a lot of time!

so my question is:

is there a simple tool for converting e.g. "hello" to "HH AH0 L OW1"

maybe some command-line tool so i can capture the stdout? i'm searching for the phonemes in 'Arpabet' style (see the 'hello' example).

espeak does something like that but the output is not in Arpabet style and the phonemes are not split by some determiner.

Tom
  • 221
  • 1
  • 4
  • 16

1 Answers1

7

If you had searched for Arpabet on wiki you would have found your answer. The CMU guys have prepared scripts which convert most english words to their respective Arpabet phonetic break up.

If you want the phone sequence of a couple of words you can use their interface here. But, if you want it for a big file then you might have to run their scripts on your own. They used to have a working page here, but it seems to be not working now.

Yakku
  • 453
  • 1
  • 7
  • 14
  • Yakku, I did search for Arpabet on google and I found the cmu dictionary but no tools or scripts for converting "every word" to phonemes... ok, the dictionary can be used for most words i guess but every speech synthesizer can figure out how to say a word not found in a dictionary.. There is no offline tool on there website either. Thanks and regards – Tom Jan 23 '15 at 15:13
  • Hi Tom, check this link out http://www.speech.cs.cmu.edu/tools/lmtool-new.html , upload your textual data in a text file and upload it here. And download the output file. The *.dic file consists of your phonetic break up. Good enough right ? :) – Yakku Jan 24 '15 at 05:22
  • Yakku, Thanks for the link :) The interesting thing is that is can translate even non existing words.. Do you have any idea how it does that? That would solve my question actually :) If i can make a tool that can do this offline that would be great :) regards! – Tom Jan 25 '15 at 15:57
  • 3
    They use a theory called letter to sound which is explained in this paper http://www.cs.cmu.edu/~awb/papers/ESCA98_lts.pdf – Yakku Jan 26 '15 at 04:22
  • Thank you Yakku, i will try to write the algorithm myself if i can't find some sourcecode on the web, regards! – Tom Jan 27 '15 at 14:41