Liu Linsong

Mr. Liu Linsong

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 June 2025 in Electronics
Verified
Journal Article
Open access
PDF file
BLBingni Li
Bingni Li
YGYu Gu
Yu Gu
CLchenyu Li
chenyu Li
HZHe Zhang
He Zhang
LLLiu Linsong
Liu Linsong
SWShuang Wang
Shuang Wang
Incorporating external knowledge has been shown to improve emotion understanding in dialogues by enriching contextual information, such as character motivations, psychological states, and causal relations between events. Filtering and categorizing this information can significantly enhance model performance. In this paper, we present an innovative Emotion Recognition in Conversation (ERC) framework, called the Scene-Speaker Emotion Awareness Network (SSEAN), which employs a dual-strategy modeling approach. SSEAN uniquely incorporates external commonsense knowledge describing speaker states into multimodal inputs. Using parallel recurrent networks to separately capture scene-level and speaker-level emotions, the model effectively reduces the accumulation of redundant information within the speaker’s emotional space. Additionally, we introduce an attention-based dynamic screening module to enhance the quality of integrated external commonsense knowledge through three levels: (1) speaker-listener-aware input structuring, (2) role-based segmentation, and (3) context-guided attention refinement. Experiments show that SSEAN outperforms existing state-of-the-art models on two well-adopted benchmark datasets in both single-text modality and multimodal settings.

30 April 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
BLBingni Li
Bingni Li
YGYu Gu
Yu Gu
CLchenyu Li
chenyu Li
HZHe Zhang
He Zhang
LLLiu Linsong
Liu Linsong
SWShuang Wang
Shuang Wang
Incorporating external knowledge has been shown to enhance emotion understanding in dialogues by supplementing contextual information across multiple aspects, including character motivations, psychological states, and event causality. Filtering and categorizing this information can significantly enhance model performance. In this paper, we present an innovative Emotion Recognition in Conversation (ERC) framework, called the Scene-Speaker Emotion Awareness Network (SSEAN), which employs a dual-strategy modeling approach. SSEAN uniquely incorporates external commonsense knowledge describing speaker states into multimodal inputs. Using parallel recurrent networks to separately capture scene-level and speaker-level emotions, the model effectively reduces the accumulation of redundant information within the speaker’s emotional space. Additionally, we introduce an attention-based dynamic screening module to enhance the quality of integrated external commonsense knowledge through three levels: (1) speaker-listener-aware input structuring, (2) role-based segmentation, and (3) context-guided attention refinement. Experiments show that SSEAN outperforms existing state-of-the-art models on two well-adopted benchmark datasets in both single-text modality and multimodal settings.

24 April 2026 in Electronics
Verified
Journal Article
Open access
PDF file
HZHe Zhang
He Zhang
ZGZichen Gao
Zichen Gao
QYQi Yan
Qi Yan
YGYu Gu
Yu Gu
SWShuang Wang
Shuang Wang
DADequan An
Dequan An
Multimodal Sentiment Analysis (MSA) integrates multiple modalities to better understand human emotions. However, existing methods often neglect heterogeneity among modal features, causing redundancy and inconsistencies. Additionally, the dynamic interplay between modalities is frequently ignored during fusion, limiting performance. To address these issues, we propose Reward-Guided Dynamic Fusion and Modality Decoupling (RDFD). RDFD includes two key components: (1) a feature decoupling module that separates modality-specific and modality-shared features, reducing redundancy and conflicts; (2) a Reward-Guided Dynamic Fusion module that adaptively selects guiding modalities to enhance modality-specific representations and enable flexible fusion. Experiments on the CMU-MOSI and CMU-MOSEI datasets show that RDFD achieves state-of-the-art performance, demonstrating its effectiveness in advancing Multimodal Sentiment Analysis.

29 January 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
LLLiu Linsong
Liu Linsong
YGYu Gu
Yu Gu
HZHe Zhang
He Zhang
SWShuang Wang
Shuang Wang
CLchenyu Li
chenyu Li
HLHai Xiang Lin
Hai Xiang Lin
With the rapid advancement of speech emotion recognition, the transition from unimodal to multimodal approaches has become inevitable. However, multimodal methods introduce new challenges, particularly classification ambiguity in complex samples when compared to unimodal approaches. To address this, we propose a Mutual Refinement Distillation (MRD) method, which incorporates three key components: (1) Modal Interaction Calibration, enhancing classification accuracy for complex samples; (2) Interactive Learning Constraints, mitigating overfitting; and (3) Reverse Curriculum Learning, further improving model robustness. Experiments with the MELD and IEMOCAP datasets demonstrate that our approach outperforms state-of-the-art methods in emotion recognition, achieving a notable 6.07% improvement over the baseline on IEMOCAP.

30 July 2025 in Electronics
Verified
Journal Article
Open access
PDF file
YDYingmin Deng
Yingmin Deng
CLchenyu Li
chenyu Li
YGYu Gu
Yu Gu
HZHe Zhang
He Zhang
LLLiu Linsong
Liu Linsong
HMHanlin Mo
Hanlin Mo
Multimodal emotion recognition (MER) is essential for understanding human emotions from diverse sources such as speech, text, and video. However, modality heterogeneity and inconsistent expression pose challenges for effective feature fusion. To address this, we propose a novel MER framework combining a Dynamic Weighted Graph Convolutional Network (DW-GCN) for feature disentanglement and a Cross-Attention Consistency-Gated Fusion (CACG-Fusion) module for robust integration. DW-GCN models complex inter-modal relationships, enabling the extraction of both common and private features. The CACG-Fusion module subsequently enhances classification performance through dynamic alignment of cross-modal cues, employing attention-based coordination and consistency-preserving gating mechanisms to optimize feature integration. Experiments on the CMU-MOSI and CMU-MOSEI datasets demonstrate that our method achieves state-of-the-art performance, significantly improving the ACC7, ACC2, and F1 scores.

12 October 2026 in Electronics
Verified
Journal Article
Open access
PDF file
LLLiu Linsong
Liu Linsong
YGYu Gu
Yu Gu
HZHe Zhang
He Zhang
SWShuang Wang
Shuang Wang
CLchenyu Li
chenyu Li
HLHai Xiang Lin
Hai Xiang Lin
With the rapid advancement of speech emotion recognition, the transition from unimodal to multimodal approaches has become inevitable. However, multimodal methods introduce new challenges, particularly classification ambiguity, where multimodal models may misclassify samples that unimodal models correctly identify, and vice versa. To address this, we propose Dynamic Adaptive Mutual Refinement (DAMR), a training framework designed to reduce classification ambiguity between multimodal and unimodal models while preserving their core architectures. DAMR incorporates three key components: (1) dynamic mutual distillation (DMD), which employs an EMA-based capability assessment mechanism and competitive dynamic weighting to adaptively adjust knowledge transfer between models; (2) adaptive inverse curriculum learning (AICL), which implements a hard-to-easy learning schedule based on information bottleneck theory and gradient signal analysis, focusing on informative and difficult samples in early training stages; and (3) an integrated optimization framework that jointly applies DMD and AICL through adaptive weighting. Experiments on the MELD and IEMOCAP datasets demonstrate that our approach outperforms state-of-the-art methods in emotion recognition, achieving a notable 5.54% improvement over the baseline on IEMOCAP.