[Corpora-List] English Syllabicification

Connie Jess adsett at cs.dal.ca
Mon Jun 20 15:12:14 UTC 2011


Hello Chris,

I'm assuming that you are working with text and not speech data.

If so, you may be interested in one of the methods described in:
- Y. Marchand, C.R. Adsett & R.I. Damper (2009) Automatic Syllabification 
in English: A Comparison of Different Algorithms. Language and Speech 
59(1):1-27
- C.R. Adsett & Y. Marchand (2009) A Comparison of Data-Driven Automatic 
Syllabification Methods. In the proceedings of SPIRE 2009 pp.174-181.

Links to these can be found here: http://web.cs.dal.ca/~adsett/

The results described and the methods compared should allow you to 
determine what trade-offs you may experience between "reasonably accurate" 
and "a simple piece of software".

You may also be limited to certain methods (especially within the 
rule-based set) depending on whether you are performing syllabification in 
the spelling or pronunciation domain.

Cheers,
Connie

>
> I'm looking for a simple piece of software to break English words up into
> syllables.  There are some based upon dictionaries such as the CMU
> Pronouncing Dictionary, but when a dictionary lookup fails I need to be able
> to fall back on to a reasonably accurate algorithm (a set of hypothetical
> syllable patterns is acceptable).
>
> Any recommendations?
>
> Thank you,
>
> Chris Fournier

_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora



More information about the Corpora mailing list