Hailun Lian

Biographic Data

ID10053937
NAMEHailun Lian
GIVEN NAMESHailun
FAMILY NAMELian
SIGNATURELIAN H
AFFILIATIONSSoutheast University
ORCID0000-0002-1355-9503
VERIFIEDYes
TOTAL WORKS4
TOTAL CITATIONS0
WORKS AS AUTHOR4
WORKS AS EDITOR0
FIRST PUBLICATION YEAR2023
LATEST PUBLICATION YEAR2026
H-INDEX0

  • An Interpretable Collaborative Acoustic Parameter Modeling Network for Speech Emotion Recognition

    Open AccessHailun Lian, Cheng Lu et al.ARTICLEIEEE Transactions on Computational…2026

    Acoustic parameters can collaboratively represent speech emotions. However, existing speech emotion recognition (SER) methods neglect explicit collaborative modeling among acoustic parameters during representation learning. This not only limits their ability to extract the information contained in acoustic parameters that collaboratively represent emotions, but also makes it difficult to trace back which acoustic parameters are closely associated…

  • Towards Domain-Specific Cross-Corpus Speech Emotion Recognition Approach

    Open AccessYan Zhao, Yuan Zong et al.ARTICLEIEEE Transactions on Computational…2025

    Cross-corpus speech emotion recognition (SER) poses a challenge due to feature distribution mismatch between the training and testing speech samples, potentially degrading the performance of established SER methods. In this article, we tackle this challenge by proposing a novel transfer subspace learning method called acoustic knowledge-guided transfer linear regression (AKTLR). Unlike existing approaches, which often overlook domain-specific kno…

  • Layer-Adapted Implicit Distribution Alignment Networks for Cross-Corpus Speech Emotion Recognition

    Open AccessYan Zhao, Yuan Zong et al.ARTICLEIEEE Transactions on Computational…2024

    In this article, we propose a new unsupervised domain adaptation (DA) method called layer-adapted implicit distribution alignment networks (LIDANs) to address the challenge of cross-corpus speech emotion recognition (SER). LIDAN extends our previous ICASSP work, deep implicit distribution alignment networks (DIDANs), whose key contribution lies in the introduction of a novel regularization term called implicit distribution alignment (IDA). This t…

  • Speech Emotion Recognition via an Attentive Time–Frequency Neural Network

    Open AccessCheng Lu, Wenming Zheng et al.ARTICLEIEEE Transactions on Computational…2023

    Spectrogram is commonly used as the input feature of deep neural networks to learn the high(er)-level time–frequency pattern of speech signal for speech emotion recognition (SER). Generally, different emotions correspond to specific energy activations both within frequency bands and time frames on spectrogram, which indicates the frequency and time domains are both essential to represent the emotion for SER. However, recent spectrogram-based work…