Transferable Positive/negative Speech Emotion Recognition Via Class-wise Adversarial Domain Adaptation

Abstract

Speech emotion recognition plays an important role in building more intelligent and human-like agents. Due to the difficulty of collecting speech emotional data, an increasingly popular solution is leveraging a related and rich source corpus to help address the target corpus. However, domain shift between the corpora poses a serious challenge, making domain shift adaptation difficult to function even on the recognition of positive/negative emotions. In this work, we propose class-wise adversarial domain adaptation to address this challenge by reducing the shift for all classes between different corpora. Experiments on the well-known corpora EMODB and Aibo demonstrate that our method is effective even when only a very limited number of target labeled examples are provided.

Stats

• citations16
• S2 citations—
• github stars0
• HF likes0
• heat score9.23
• arxiv keyzhou2018transferable

Related papers

• Domain Adversarial Learning For Emotion Recognition (2019)0.00
• Self Supervised Adversarial Domain Adaptation For Cross-corpus And Cross-language Speech Emotion Recognition (2022)13.11
• Improving Speaker-independent Speech Emotion Recognition Using Dynamic Joint Distribution Adaptation (2024)7.50
• Transfer Learning For Improving Speech Emotion Classification Accuracy (2018)15.10
• Unsupervised Cross-lingual Speech Emotion Recognition Using Domainadversarial Neural Network (2020)0.00
• Acted Vs. Improvised: Domain Adaptation For Elicitation Approaches In Audio-visual Emotion Recognition (2021)0.00
• Unsupervised Adversarial Domain Adaptation For Cross-lingual Speech Emotion Recognition (2019)12.74
• Embedded Emotions -- A Data Driven Approach To Learn Transferable Feature Representations From Raw Speech Input For Emotion Recognition (2020)0.00