location: Current position: Home >> Scientific Research >> Paper Publications

Gradformer: A Framework for Multi-Aspect Multi-Granularity Pronunciation Assessment

Hits:

Affiliation of Author(s):软件学院

Journal:: IEEE/ACM Transactions on Audio, Speech, and Language Processing

First Author:裴皓辰

Document Code:1318F14F31CE4E38B84003E410E45E0B

Issue:11

Number of Words:10

Translation or Not:no

Date of Publication:2023-11-23

Pre One:ProtoUDA: Prototype-based Unsupervised Adaptation for Cross-Domain Text Recognition

Next One:VOLTER: Visual Collaboration and Dual-Stream Fusion for Scene Text Recognition