all AI news
Improving generalizability of distilled self-supervised speech processing models under distorted settings. (arXiv:2210.07978v2 [cs.SD] UPDATED)
Oct. 21, 2022, 1:18 a.m. | Kuan-Po Huang, Yu-Kuan Fu, Tsu-Yuan Hsu, Fabian Ritter Gutierrez, Fan-Lin Wang, Liang-Hsuan Tseng, Yu Zhang, Hung-yi Lee
cs.CL updates on arXiv.org arxiv.org
Self-supervised learned (SSL) speech pre-trained models perform well across
various speech processing tasks. Distilled versions of SSL models have been
developed to match the needs of on-device speech applications. Though having
similar performance as original SSL models, distilled counterparts suffer from
performance degradation even more than their original versions in distorted
environments. This paper proposes to apply Cross-Distortion Mapping and Domain
Adversarial Training to SSL models during knowledge distillation to alleviate
the performance gap caused by the domain mismatch problem. …
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US