I am looking for a forced aligner in Spanish. Something similar to P2FA for American English.
I want to force align simple sentences in Mexican Spanish for a project.
Does anyone know one?
Linguistics Stack Exchange is a question and answer site for professional linguists and others with an interest in linguistic research and theory. It only takes a minute to sign up.
Sign up to join this communityThere's also the relatively new PraatAlign plugin (https://github.com/dopefishh/praatalign). I know that Easy-Align is trained on Castilian models and might not be the best for your Mexican data. The documentation for PraatAlign is a little vague on the variety used for training data, but looking at their phone inventory it appears to be a seseo-variety with the palatal lateral so I'm thinking Sevilla or Córdoba. Either way, you could edit either dictionary for your variety.
In my lab we're also working on a Spanish variant of P2FA built using Latin American sociolinguistic interviews as training data. If you're still working on the project, send me a message if you're interested in more information.
This is a response to Eric answer but I can't seem to add comments...
Praatalign uses the models trained by Schiel et al. from München.
Praatalign phonetizes Spanish orthographic transcription on the fly but is also able to apply inter/intra-word pronunciation rules and one or more alternative pronunciations via a pronunciation dictionary.
Just Googling, I found this:
http://latlntic.unige.ch/phonetique/easyalign.php
I don't know anything about it, but they claim to be able to handle French, Spanish, and English.
Coming back to my own question posted a few years ago, I have had a lot of sucsess with faseAlign. Here is a link to the documentation: faseAlign Documentation