Cross-lingual Matryoshka Representation Learning across Speech and Text
This addresses the language and modality barriers for speakers of under-represented languages like Wolof, though it is incremental as it builds on existing Matryoshka embedding techniques.
The paper tackled the problem of cross-lingual retrieval for under-represented languages by training a bilingual speech-text Matryoshka embedding model for French-Wolof, enabling efficient retrieval of French text from Wolof speech queries without costly pipelines, and showed that modality fusion within a frozen text model performs best while generalizing to other tasks like speech intent detection.
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.