activity
20222024
most citedLearning a Structural Causal Model for Intuition Reasoning in Conversation

16 citations · 18 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL2024

Skipformer: A Skip-and-Recover Strategy for Efficient Speech Recognition

Wenjing Zhu, Sining Sun, Changhao Shan +2

Conformer-based attention models have become the de facto backbone model for Automatic Speech Recognition tasks. A blank symbol is usually introduced to align the input and output…

cs.CL2023★ 16 cited

Learning a Structural Causal Model for Intuition Reasoning in Conversation

Hang Chen, Bingyu Liao, Jing Luo +2

Reasoning, a crucial aspect of NLP research, has not been adequately addressed by prevailing models including Large Language Model. Conversation reasoning, as a critical component…

cs.CL2023

How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoning

Hang Chen, Jing Luo, Xinyu Yang +1

Our investigation into the Affective Reasoning in Conversation (ARC) task highlights the challenge of causal discrimination. Almost all existing models, including large language mo…

cs.SD2023★ 1 cited

Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by Discriminative Learning

Zhaoxi Mu, Xinyu Yang, Wenjing Zhu

Transformer has shown advanced performance in speech separation, benefiting from its ability to capture global features. However, capturing local features and channel information o…

cs.SD2023★ 1 cited

A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant Environments

Zhaoxi Mu, Xinyu Yang, Xiangyuan Yang +1

In noisy and reverberant environments, the performance of deep learning-based speech separation methods drops dramatically because previous methods are not designed and optimized f…

cs.SD2022

Speech Emotion Recognition with Global-Aware Fusion on Multi-scale Feature Representation

Wenjing Zhu, Xiang Li

Speech Emotion Recognition (SER) is a fundamental task to predict the emotion label from speech data. Recent works mostly focus on using convolutional neural networks~(CNNs) to lea…