AlloVera: a multilingual allophone database

• DOI: 10.48550/arxiv.2004.08031
• Publication Date: 2020-01-01
• Authors: Mortensen, David,; Li, Xinjian; Littell, Patrick; Michaud, Alexis; Rijhwani, Shruti; Anastasopoulos, A...; Black, Alan; Metze, Florian; Neubig, Graham
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; Allophones; automatic speech recognition; Phoneme; phonology; allophones; 03 medical and health sciences; [SHS.LANGUE]Humanities and Social Sciences/Linguistics; 0305 other medical science; [SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing; Computation and Language (cs.CL); database

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.<br/>8 pages, LREC 2020<br/>