# Tone recognition in low-resource languages of North-East India: peeling the layers of SSL-based speech models

arXiv: https://arxiv.org/abs/2506.03606 · HTML: https://mlsanity.com/paper/2506.03606/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 33 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Layer-wise Analysis of a Self-supervised Speech Representation Model](https://mlsanity.com/paper/2107.04734/) (2021)
- [Self-Supervised Speech Representation Learning: A Review](https://mlsanity.com/paper/2205.10643/) (2022)
- [Encoding of lexical tone in self-supervised models of spoken language](https://mlsanity.com/paper/2403.16865/) (2024)
- [What Can an Accent Identifier Learn? Probing Phonetic and Prosodic Information in a Wav2vec2-based Accent Identification Model](https://mlsanity.com/paper/2306.06524/) (2023)
- [A layer-wise analysis of Mandarin and English suprasegmentals in SSL speech models](https://mlsanity.com/paper/2408.13678/) (2024)
- [Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect](https://mlsanity.com/paper/2407.04533/) (2024)
- [End-to-End Mandarin Tone Classification with Short Term Context Information](https://mlsanity.com/paper/2104.05657/) (2021)

## Built on by (most cited first, 1 of 1)

- [How Far Do SSL Speech Models Listen for Tone? Temporal Focus of Tone Representation under Low-resource Transfer](https://mlsanity.com/paper/2511.12285/) (2025)

## Abstract (arXiv)

This study explores the use of self-supervised learning (SSL) models for tone recognition in three low-resource languages from North Eastern India: Angami, Ao, and Mizo. We evaluate four Wav2vec2.0 base models that were pre-trained on both tonal and non-tonal languages. We analyze tone-wise performance across the layers for all three languages and compare the different models. Our results show that tone recognition works best for Mizo and worst for Angami. The middle layers of the SSL models are the most important for tone recognition, regardless of the pre-training language, i.e. tonal or non-tonal. We have also found that the tone inventory, tone types, and dialectal variations affect tone recognition. These findings provide useful insights into the strengths and weaknesses of SSL-based embeddings for tonal languages and highlight the potential for improving tone recognition in low-resource settings. The source code is available at GitHub 1 .