AlloVera: A Multilingual Allophone Database
This resource aids in documenting endangered and minority languages by providing a universal phonetic transcription tool, though it is incremental as it builds on existing phonetics and speech recognition methods.
The authors introduced AlloVera, a multilingual database mapping 218 allophones to phonemes across 14 languages, enabling speech recognition models to output phonetic transcriptions in IPA regardless of input language. They showed that Allosaurus, a universal allophone model built with AlloVera, outperformed universal phonemic and language-specific models on a speech-transcription task.
We introduce a new resource, AlloVera, which provides mappings from 218 allophones to phonemes for 14 languages. Phonemes are contrastive phonological units, and allophones are their various concrete realizations, which are predictable from phonological context. While phonemic representations are language specific, phonetic representations (stated in terms of (allo)phones) are much closer to a universal (language-independent) transcription. AlloVera allows the training of speech recognition models that output phonetic transcriptions in the International Phonetic Alphabet (IPA), regardless of the input language. We show that a "universal" allophone model, Allosaurus, built with AlloVera, outperforms "universal" phonemic models and language-specific models on a speech-transcription task. We explore the implications of this technology (and related technologies) for the documentation of endangered and minority languages. We further explore other applications for which AlloVera will be suitable as it grows, including phonological typology.