255
Views
0
CrossRef citations to date
0
Altmetric
Research Article

Bi-Modal Bi-Task Emotion Recognition Based on Transformer Architecture

&
Article: 2356992 | Received 02 Jan 2024, Accepted 13 May 2024, Published online: 21 May 2024

Figures & data

Figure 1. Comparison between bimodal dual-task emotion recognition methods and traditional methods.

Figure 1. Comparison between bimodal dual-task emotion recognition methods and traditional methods.

Figure 2. Network architecture diagram.

Figure 2. Network architecture diagram.

Table 1. Algorithm comparison on the IEMOCAP dataset.

Table 2. Algorithm comparison on the RAVDESS dataset.

Figure 3. Confusion matrix of the model in the IEMOCAP dataset.

Figure 3. Confusion matrix of the model in the IEMOCAP dataset.

Figure 4. Confusion matrix of the model in the REVDESS dataset.

Figure 4. Confusion matrix of the model in the REVDESS dataset.

Figure 5. Feature distribution learned under the supervision of cross-entropy loss function on the IEMOCAP dataset.

Figure 5. Feature distribution learned under the supervision of cross-entropy loss function on the IEMOCAP dataset.

Figure 6. Feature distributions learned under the supervision of both cross-entropy and N-pair loss function on the IEMOCAP dataset.

Figure 6. Feature distributions learned under the supervision of both cross-entropy and N-pair loss function on the IEMOCAP dataset.

Figure 7. Ablation experiments based on the IEMOCAP dataset.

Figure 7. Ablation experiments based on the IEMOCAP dataset.

Data Availability Statement

The data used to support the findings of this study are included within the article.