Investigating Transcription Normalization in the Faetar ASR Benchmark
Not on the map. Why?
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.
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
7 of 15 references.
References · 7
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
- 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
- 2024An Embarrassingly Simple Approach for LLM with Strong ASR Capacitycited by 88
- 2020Universal Phone Recognition with a Multilingual Allophone Systemcited by 81
- 2020An investigation of phone-based subword units for end-to-end speech recognitioncited by 12
- 2024Quantifying the Role of Textual Predictability in Automatic Speech Recognitioncited by 2
- 2025Data-Driven Mispronunciation Pattern Discovery for Robust Speech Recognitioncited by 2
Built on by
Not cited yet.