Abstract

Self-supervised learning (SSL) models extract rich speech representations but often come with high-dimensional features, increasing computational complexity. This work explores an SSL-AutoEncoder (SSL-AE) bottlenecking approach to efficiently reduce feature dimensions while maintaining dysarthric Automatic Speech Recognition (ASR) performance. By leveraging an autoencoder, we transform high-dimensional SSL features into a compact space, reducing model complexity and training time. Our method preserves essential speech information, achieving reduced Word Error Rates (WER) while significantly lowering computational costs. Experiments show SSL-AE bottlenecking reduces training time by compared to the SSL baseline, demonstrating efficiency without sacrificing recognition performance. These results highlight AE as an effective solution for SSL feature compression in resource-constrained …

Date

2026

Authors

Paban Sapkota, Hemant Kumar Kathania, Mikko Kurimo, Shrikanth Narayanan, Sudarsana Reddy Kadiri

Conference

2026 National Conference on Communications (NCC)

Pages

590-595

Publisher

IEEE