# Investigating Transcription Normalization in the Faetar ASR Benchmark

arXiv: https://arxiv.org/abs/2508.11771 · HTML: https://mlsanity.com/paper/2508.11771/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Builds on (most cited first, 7 of 7)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [An Embarrassingly Simple Approach for LLM with Strong ASR Capacity](https://mlsanity.com/paper/2402.08846/) (2024)
- [Universal Phone Recognition with a Multilingual Allophone System](https://mlsanity.com/paper/2002.11800/) (2020)
- [An investigation of phone-based subword units for end-to-end speech recognition](https://mlsanity.com/paper/2004.04290/) (2020)
- [Quantifying the Role of Textual Predictability in Automatic Speech Recognition](https://mlsanity.com/paper/2407.16537/) (2024)
- [Data-Driven Mispronunciation Pattern Discovery for Robust Speech Recognition](https://mlsanity.com/paper/2502.00583/) (2025)

## Abstract (arXiv)

We examine the role of transcription inconsistencies in the Faetar Automatic Speech Recognition benchmark, a challenging low-resource ASR benchmark. With the help of a small, hand-constructed lexicon, we conclude that find that, while inconsistencies do exist in the transcriptions, they are not the main challenge in the task. We also demonstrate that bigram word-based language modelling is of no added benefit, but that constraining decoding to a finite lexicon can be beneficial. The task remains extremely difficult.