@techreport{oai:ipsj.ixsq.nii.ac.jp:02000477,
 author = {Jaeyoung,Lee and Tatsuya,Kawahara and Jaeyoung Lee and Tatsuya Kawahara},
 issue = {4},
 month = {Feb},
 note = {Large pretrained ASR models achieve state-of-the-art performance but are computationally expensive. The Lottery Ticket Hypothesis (LTH) hypothesizes that there exist sparse subnetworks, or “winning tickets,” that can match the performance of the full model. This study applies LTH to a large pretrained ASR model, namely XLS-R, demonstrating that winning tickets exist at up to 60% sparsity while maintaining accuracy. Using a subset of Common Voice covering 90 languages, we find that moderate pruning (80%-51% of the model size) enhances generalization, consistent with prior LTH findings. Our results confirm LTH's applicability to large ASR models, opening new avenues for efficient and scalable speech recognition., Large pretrained ASR models achieve state-of-the-art performance but are computationally expensive. The Lottery Ticket Hypothesis (LTH) hypothesizes that there exist sparse subnetworks, or “winning tickets,” that can match the performance of the full model. This study applies LTH to a large pretrained ASR model, namely XLS-R, demonstrating that winning tickets exist at up to 60% sparsity while maintaining accuracy. Using a subset of Common Voice covering 90 languages, we find that moderate pruning (80%-51% of the model size) enhances generalization, consistent with prior LTH findings. Our results confirm LTH's applicability to large ASR models, opening new avenues for efficient and scalable speech recognition.},
 title = {Winning Tickets in Large Pretrained Speech Models: Exploring the Lottery Ticket Hypothesis in XLS-R},
 year = {2025}
}