# Cross-lingual Matryoshka Representation Learning across Speech and Text

arXiv: https://arxiv.org/abs/2602.19991 · HTML: https://mlsanity.com/paper/2602.19991/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech](https://mlsanity.com/paper/2205.12446/) (2022)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [On decoder-only architecture for speech-to-text and large language model integration](https://mlsanity.com/paper/2307.03917/) (2023)
- [Efficient Few-Shot Learning Without Prompts](https://mlsanity.com/paper/2209.11055/) (2022)
- [Powerset multi-class cross entropy loss for neural speaker diarization](https://mlsanity.com/paper/2310.13025/) (2023)
- [Answer is All You Need: Instruction-following Text Embedding via Answering the Question](https://mlsanity.com/paper/2402.09642/) (2024)
- [Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation](https://mlsanity.com/paper/2503.01776/) (2025)
- [SMEC: Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression](https://mlsanity.com/paper/2510.12474/) (2025)
- [Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs](https://mlsanity.com/paper/2503.06362/) (2025)
- [Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages](https://mlsanity.com/paper/2406.12739/) (2024)
- [Kallaama: A Transcribed Speech Dataset about Agriculture in the Three Most Widely Spoken Languages in Senegal](https://mlsanity.com/paper/2404.01991/) (2024)
- [Prepending or Cross-Attention for Speech-to-Text? An Empirical Comparison](https://mlsanity.com/paper/2501.02370/) (2025)
- [Speech Language Models for Under-Represented Languages: Insights from Wolof](https://mlsanity.com/paper/2509.15362/) (2025)
- [Revisiting Direct Speech-to-Text Translation with Speech LLMs: Better Scaling than CoT Prompting?](https://mlsanity.com/paper/2510.03093/) (2025)

## Abstract (arXiv)

Speakers of under-represented languages face both a language barrier, as most online knowledge is in a few dominant languages, and a modality barrier, since information is largely text-based while many languages are primarily oral. We address this for French-Wolof by training the first bilingual speech-text Matryoshka embedding model, enabling efficient retrieval of French text from Wolof speech queries without relying on a costly ASR-translation pipelines. We introduce large-scale data curation pipelines and new benchmarks, compare modeling strategies, and show that modality fusion within a frozen text Matryoshka model performs best. Although trained only for retrieval, the model generalizes well to other tasks, such as speech intent detection, indicating the learning of general semantic representations. Finally, we analyze cost-accuracy trade-offs across Matryoshka dimensions and ranks, showing that information is concentrated only in a few components, suggesting potential for efficiency improvements.