# Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models

arXiv: https://arxiv.org/abs/2509.17523 · HTML: https://mlsanity.com/paper/2509.17523/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [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)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [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)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling](https://mlsanity.com/paper/2011.11588/) (2020)
- [Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset](https://mlsanity.com/paper/2205.12522/) (2022)
- [Robust Self-Supervised Audio-Visual Speech Recognition](https://mlsanity.com/paper/2201.01763/) (2022)
- [SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model](https://mlsanity.com/paper/2210.00705/) (2022)
- [Vision as an Interlingua: Learning Multilingual Semantic Embeddings of Untranscribed Speech](https://mlsanity.com/paper/1804.03052/) (2018)
- [Self-Supervised Representation Learning for Speech Using Visual Grounding and Masked Language Modeling](https://mlsanity.com/paper/2202.03543/) (2022)
- [XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception](https://mlsanity.com/paper/2403.14402/) (2024)
- [M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval](https://mlsanity.com/paper/2211.01180/) (2022)
- [fastabx: A library for efficient computation of ABX discriminability](https://mlsanity.com/paper/2505.02692/) (2025)
- [A Comparative Analysis of Bilingual and Trilingual Wav2Vec Models for Automatic Speech Recognition in Multilingual Oral History Archives](https://mlsanity.com/paper/2407.17160/) (2024)
- [Simultaneous or Sequential Training? How Speech Representations Cooperate in a Multi-Task Self-Supervised Learning System](https://mlsanity.com/paper/2306.02972/) (2023)

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

- [Language Discrimination Improves Linguistic Learning in Multilingual Speech Models](https://mlsanity.com/paper/2609.33345/) (2026)

## Abstract (arXiv)

Self-supervised learning (SSL) has made significant advances in speech representation learning. Models like wav2vec 2.0 and HuBERT have achieved state-of-the-art results in tasks such as speech recognition, particularly in monolingual settings. However, multilingual SSL models tend to underperform their monolingual counterparts on each individual language, especially in multilingual scenarios with few languages such as the bilingual setting. In this work, we investigate a novel approach to reduce this performance gap by introducing limited visual grounding into bilingual speech SSL models. Our results show that visual grounding benefits both monolingual and bilingual models, with especially pronounced gains for the latter, reducing the multilingual performance gap on zero-shot phonetic discrimination from 31.5% for audio-only models to 8.04% with grounding.