# Quantifying Language Variation Acoustically with Few Resources

arXiv: https://arxiv.org/abs/2205.02694 · HTML: https://mlsanity.com/paper/2205.02694/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 40 references that are in the map.
- First posted on arXiv 5 May 2022.

## Builds on (most cited first, 10 of 10)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Universal Phone Recognition with a Multilingual Allophone System](https://mlsanity.com/paper/2002.11800/) (2020)
- [Probing Acoustic Representations for Phonetic Properties](https://mlsanity.com/paper/2010.13007/) (2020)
- [Neural Representations for Modeling Variation in Speech](https://mlsanity.com/paper/2011.12649/) (2020)
- [Adapting Monolingual Models: Data can be Scarce when Language Similarity is High](https://mlsanity.com/paper/2105.02855/) (2021)

## Built on by (most cited first, 12 of 12)

- [Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation](https://mlsanity.com/paper/2305.10951/) (2023)
- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens](https://mlsanity.com/paper/2402.02302/) (2024)
- [Self-supervised Speech Representations Still Struggle with African American Vernacular English](https://mlsanity.com/paper/2408.14262/) (2024)
- [Leveraging supplementary text data to kick-start automatic speech recognition system development with limited transcriptions](https://mlsanity.com/paper/2302.04975/) (2023)
- [AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accents](https://mlsanity.com/paper/2402.01152/) (2024)
- [Improving Child Speech Recognition and Reading Mistake Detection by Using Prompts](https://mlsanity.com/paper/2506.11079/) (2025)
- [Automated Tone Transcription and Clustering with Tone2Vec](https://mlsanity.com/paper/2410.02324/) (2024)
- [Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models](https://mlsanity.com/paper/2510.02569/) (2025)
- [Reading Miscue Detection in Primary School through Automatic Speech Recognition](https://mlsanity.com/paper/2406.07060/) (2024)
- [Dialetto, ma Quanto Dialetto? Transcribing and Evaluating Dialects on a Continuum](https://mlsanity.com/paper/2410.14589/) (2024)
- [Towards Comprehensive Semantic Speech Embeddings for Chinese Dialects](https://mlsanity.com/paper/2601.07274/) (2026)

## Abstract (arXiv)

Deep acoustic models represent linguistic information based on massive amounts of data. Unfortunately, for regional languages and dialects such resources are mostly not available. However, deep acoustic models might have learned linguistic information that transfers to low-resource languages. In this study, we evaluate whether this is the case through the task of distinguishing low-resource (Dutch) regional varieties. By extracting embeddings from the hidden layers of various wav2vec 2.0 models (including new models which are pre-trained and/or fine-tuned on Dutch) and using dynamic time warping, we compute pairwise pronunciation differences averaged over 10 words for over 100 individual dialects from four (regional) languages. We then cluster the resulting difference matrix in four groups and compare these to a gold standard, and a partitioning on the basis of comparing phonetic transcriptions. Our results show that acoustic models outperform the (traditional) transcription-based approach without requiring phonetic transcriptions, with the best performance achieved by the multilingual XLSR-53 model fine-tuned on Dutch. On the basis of only six seconds of speech, the resulting clustering closely matches the gold standard.