Preprint
Abstract
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.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Cross-Lingual Consistency of Phonological Features: An Empirical Study2019
- AISHELL-1: An open-source Mandarin speech corpus and a speech recognition baseline2017
- Voice Onset Time (VOT) at 50: Theoretical and practical issues in measuring voicing distinctionsJournal of Phonetics, 2017
- Documentary Linguistics: Methodological Challenges and Innovatory ResponsesApplied Linguistics, 2016
- An Amharic speech corpus for large vocabulary continuous speech recognition2005
- An introduction to phonetics and phonology . By John Clark and Colin Yallop. Oxford & Cambridge, MA: Basil Blackwell, 1990. Pp. xiv, 400. $24.95.Language, 1992
- Phonology in Generative GrammarWORD, 1962