Missing Words: Semi-automated approach

Comments

Flat

User: Sergey
Date: 4/20/2008 9:36 am

Views: 1678
Rating: 20 Rate [ ]

Hello Ken,
I was trying to segment a real audio book now, and as expected, it has missing words. Step 2 of the tutorial "Add Missing Words: Semi-automated approach using Festival" suggests running MissingWOrdsCleanup.pl script. When I run it, I get an error:

/a/proj/voxforge$ ./missingwordscleanup.pl
festival -b MissingWordsPhonemes.scm
SIOD ERROR: not a symbol or string : (quote S)
closing a file left open: temp
closing a file left open: MissingWords
closing a file left open: MissingWordsPhonemes.scm
system festival -b MissingWordsPhonemes.scm failed: 65280 at ./missingwordscleanup.pl line 51.
/a/proj/voxforge$

and it creates an empty file MissingWords_out.
What might be wrong ?
Thanks,
--Sergey

Reply •

Re: Missing Words: Semi-automated approach

User: Sergey
Date: 4/20/2008 9:54 am

Views: 148
Rating: 21 Rate [ ]

I think I have found the reason for this error and a workaround. There were words in MissingWords with a qute mark (like VIPER'S). I removed all the quotes manually (like VIPERS) and it works now.
Is it the best solution?

Reply •

Re: Missing Words: Semi-automated approach

User: kmaclean
Date: 4/21/2008 4:52 pm

Views: 151
Rating: 24 Rate [ ]

Hi Sergey,

>I removed all the quotes manually (like VIPERS) and it works now. Is it the best solution?

Yes ... the script manually removes double quotes, but not single quotes. Single quotes are a little tricky, because sometimes you need them for some words in your pronounciation dictionary. But Festival does not like quotes - and gives you an error.

By changing them manually, Festival will give you the correct pronounciation (or at least agive you a good start to a good pronounciation), and you can put back the quote when you update your prononuciation dictionary.

Ken

Reply •

Re: Missing Words: Semi-automated approach

User: Sergey
Date: 4/22/2008 7:31 am

Views: 181
Rating: 27 Rate [ ]

Hi Ken,
Thanks for the great explanation!
--Sergey

Reply •

Previous • Next • Add •


Username	Password