5 citations · 11 across the 8 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.LG2022★ 5 cited
Self-supervised Speaker Recognition Training Using Human-Machine Dialogues
Metehan Cekic, Ruirui Li, Zeya Chen +3
Speaker recognition, recognizing speaker identities based on voice alone, enables important downstream applications, such as personalization and authentication. Learning speaker re…
cs.NE2022
Neuro-Inspired Deep Neural Networks with Sparse, Strong Activations
Metehan Cekic, Can Bakiskan, Upamanyu Madhow
While end-to-end training of Deep Neural Networks (DNNs) yields state of the art performance in an increasing array of applications, it does not provide insight into, or control ov…