# AlloVera: A Multilingual Allophone Database

arXiv: https://arxiv.org/abs/2004.08031 · HTML: https://mlsanity.com/paper/2004.08031/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [ASR2K: Speech Recognition for Around 2000 Languages without Audio](https://mlsanity.com/paper/2209.02842/) (2022)
- [Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes](https://mlsanity.com/paper/2306.04306/) (2023)
- [Differentiable Allophone Graphs for Language-Universal Speech Recognition](https://mlsanity.com/paper/2107.11628/) (2021)
- [Scaling A Simple Approach to Zero-Shot Speech Recognition](https://mlsanity.com/paper/2407.17852/) (2024)
- [Tusom2021: A Phonetically Transcribed Speech Dataset from an Endangered Language for Universal Phone Recognition Experiments](https://mlsanity.com/paper/2104.00824/) (2021)
- [BranchShine: Compact Raw-Audio-to-IPA Transcription with a RoPE E-Branchformer Encoder](https://mlsanity.com/paper/2606.22824/) (2026)
- [Spoken Term Detection Methods for Sparse Transcription in Very Low-resource Settings](https://mlsanity.com/paper/2106.06160/) (2021)
- [UniGlyph: A Seven-Segment Script for Universal Language Representation](https://mlsanity.com/paper/2410.08974/) (2024)
- [Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models](https://mlsanity.com/paper/2606.11639/) (2026)
- [BranchShine-CR: Compact Multilingual IPA Transcription with Self-Conditioned CTC and Consistency Regularization](https://mlsanity.com/paper/2609.29069/) (2026)

## Abstract (arXiv)

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.