"DVSA: A focused and efficient sparse attention via explicit selection for ..."

Minghan Zhang et al. (2025)

> Home

Details and statistics

DOI: 10.1016/J.SPECOM.2025.103300

access: closed

type: Journal Article

metadata version: 2025-10-14

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - journals/speech/ZhangSXSGW25
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/speech/ZhangSXSGW25
Minghan Zhang, Jing Song, Fei Xie, Ke Shi, Zhiyuan Guo, Fuliang Weng:
DVSA: A focused and efficient sparse attention via explicit selection for speech recognition. Speech Commun. 174: 103300 (2025)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.