← Search

Jinwen Huang

2 accepted papers

2024

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models

ACL 2024long

Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of training dataset, training method, and evaluation benchmark. In t…

2023

Dynamic TF-TDNN: Dynamic Time Delay Neural Network Based on Temporal-Frequency Attention for Dialect Recognition

ICASSP 2023accepted

Dialect recognition aims to recognize dialect categories in utterances, which has been applied in many audio applications. Recently, various Time Delayed Neural Network (TDNN) based AI models are proposed to solve dialect recognition problems, such as D-TDNN, DMC-TDNN, and ECAPA-TDNN, however, most…

Cited by 0SourceScholar