← Search

Linsong Liu

2 accepted papers

2025

Hybrid Contrastive Learning Decoupling Speech Emotion Recognition

ICASSP 2025accepted

Speech signals contain rich information, such as textual content, emotion, and speaker identity. To extract these features more efficiently, researchers are investigating joint training across multiple tasks, like Speech Emotion Recognition (SER) and Speaker Verification (SV), aiming to improve perf…

Cited by 0SourceScholar
2025

TDMER: A Task-Driven Method for Multimodal Emotion Recognition

ICASSP 2025accepted

In multimodal emotion recognition, disentangled representation learning method effectively address the inherent heterogeneity among modalities. To facilitate the flexible integration of enhanced disentangled features into multimodal emotional features, we propose a task-driven multimodal emotion rec…

Cited by 0SourceScholar