Spanish Phonology Tagger

This annotator tags Spanish words their phonemic transcription, based on rules that map orthography to phonology

Rule-based conversion is based on spanish-pronunciation-rules-php, an open-source PHP function that converts a Spanish word into IPA phonetic transcription symbols, written by Timur Baytukalov, http://easypronunciation.com/en/

The annotator's spelling-to-pronuncation rules are context-sensitive within the word. Some example transcriptions are:

word phonemes word phonemes word phonemes
año → aɲo qué → kE mi → mi
mí → mi jaja → xaxa baño → baɲo
abajo → aβaxo vaso → baso oveja → oβexa
harto → aɾto charla → ʧaɾla dedo → deðo
agua → aɣwa gesto → xesto grande → gɾande
colgar → kolgaɾ tango → taŋgo tanto → tanto
Danbo → dambo nínfa → nimfa convenir → kombeniɾ
conllevar → koɲʎeβaɾ conyugal → koɲʝuɣal ala → ala
allá → aʎa rollo → roʎo pero → peɾo
perro → pero enredo → enreðo alrededor → alreðeðoɾ
éxito → eksito México → mexiko

The annotator currently supports two varieties of Spanish; Spain and Mexico. Some illustrative examples of the differences in transcription are given below:

word Spain Mexico
hacia → aθja asja
Jacinta → xaθinta xasinta
desregulación → desreɣulaθjon desreɣulasjon
vergüenza → beɾɣwenθa beɾɣwensa