Search papers, labs, and topics across Lattice.
University of Maryland College Park
3
0
1
Achieving a 23.99% reduction in speaker verification errors in noisy classroom conditions could revolutionize AI applications in education.
Achieving high accuracy in speech inversion across multiple languages reveals the potential for universal models in speech processing.
Self-supervised representations can boost diffusion-based speech enhancement, yielding a significant 0.4 improvement in PESQ scores.
