Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing

Autor: Huang, Hukai, Lu, Shenghui, Shan, Yahui, Qu, He, Zhang, Fengrun, Guan, Wenhao, Hong, Qingyang, Li, Lin

The Mixture of Experts (MoE) model is a promising approach for handling code-switching speech recognition (CS-ASR) tasks. However, the existing CS-ASR work on MoE has yet to leverage the advantages of MoE's parameter scaling ability fully. This work

Externí odkaz: http://arxiv.org/abs/2407.18581

Exploring Asynchronous Online Courses in Language Group V: A Case of Intermediate Korean

Autor: Seung-Eun Chang

Publikováno v: Journal of the National Council of Less Commonly Taught Languages, Vol 36, Iss S1, Pp 165-220 (2024)

While asynchronous online language courses have been increasingly implemented in higher-education environments, they have limited use for Language Group V. This study explores the curriculum design and efficacy of an asynchronous online mode for an i

Externí odkaz: https://doaj.org/article/9116907ab01146049f705ecf26b376fd

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Invitation to join the Healthcare AI Language Group: HeALgroup.AI Initiative.

Autor: Staubli SM; Organ Transplant Center of Excellence, King Faisal Specialist Hospital and Research Center, Riyadh, Saudi Arabia s.staubli@nhs.net., Jobeir B; Organ Transplant Center of Excellence, King Faisal Specialist Hospital and Research Center, Riyadh, Saudi Arabia., Spiro M; Organ Transplant Center of Excellence, King Faisal Specialist Hospital and Research Center, Riyadh, Saudi Arabia., Raptis DA; Organ Transplant Center of Excellence, King Faisal Specialist Hospital and Research Center, Riyadh, Saudi Arabia.

Publikováno v: BMJ health & care informatics [BMJ Health Care Inform] 2024 Mar 12; Vol. 31 (1). Date of Electronic Publication: 2024 Mar 12.

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.