Evaluating the Effect of Linguistic Relatedness on Cross-Lingual Transfer in Large Multilingual Automatic Speech Recognition
This work challenges the assumption that linguistic relatedness aids cross-lingual transfer in large ASR models, which is relevant for researchers developing ASR for low-resource languages.
The study investigates whether linguistic relatedness improves cross-lingual transfer in large multilingual ASR models for low-resource African languages. Across multiple conditions, pre-adaptation on related auxiliary languages yielded no practically meaningful improvements, suggesting linguistic relatedness alone is not an effective strategy.
Extending automatic speech recognition (ASR) to low-resource African languages is constrained by the prohibitive demands of data collection at scale. A promising direction is to leverage linguistic relatedness to enhance cross-lingual transfer from a related auxiliary language to the low-resource target by sequentially adapting on both. Although this strategy has shown meaningful improvements in small ASR models, its effectiveness in large ASR remains unclear. We extend this framework to large multilingual ASR through a systematic controlled experimental design spanning six factors, two Africa-centric corpora, and four large ASR models, isolating whether linguistic relatedness reliably predicts cross-lingual transfer gains in this setting. Across all conditions, pre-adaptation on related auxiliary languages yields no practically meaningful transfer improvements given minimal target-language data, suggesting that linguistic relatedness alone may not reliably predict cross-lingual transfer gains in large multilingual ASR, or constitute an effective strategy for extending such models to low-resource languages.