Enhancing end-to-end speech translation via multi-stage knowledge distillation.

Saved in:
Bibliographic Details
Title: Enhancing end-to-end speech translation via multi-stage knowledge distillation.
Authors: Zhou Y; School of Informatics, Xiamen University, Xiamen, 361005, Fujian, China; Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan, Ministry of Culture and Tourism, China. Electronic address: zhouyue1@stu.xmu.edu.cn., Yuan Y; School of Informatics, Xiamen University, Xiamen, 361005, Fujian, China; Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan, Ministry of Culture and Tourism, China. Electronic address: yuanyuxuan@stu.xmu.edu.cn., Feng Y; School of Electronics and Information Engineering, South China Normal University, Foshan, China. Electronic address: fengyanyan@m.scnu.edu.cn., Shi X; School of Informatics, Xiamen University, Xiamen, 361005, Fujian, China; Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan, Ministry of Culture and Tourism, China. Electronic address: mandel@xmu.edu.cn.
Source: Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2026 May; Vol. 197, pp. 108444. Date of Electronic Publication: 2025 Dec 06.
Publication Type: Journal Article
Journal Info: Publisher: Pergamon Press Country of Publication: United States NLM ID: 8805018 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1879-2782 (Electronic) Linking ISSN: 08936080 NLM ISO Abbreviation: Neural Netw Subsets: MEDLINE
Database: MEDLINE Ultimate
Description
ISSN:1879-2782
DOI:10.1016/j.neunet.2025.108444