What Does it Take to Generalize SER Model Across Datasets? A Comprehensive Benchmark
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910487464116224 |
|---|---|
| author | Ibrahim, Adham Shehata, Shady Kulkarni, Ajinkya Mohamed, Mukhtar Abdul-Mageed, Muhammad |
| author_facet | Ibrahim, Adham Shehata, Shady Kulkarni, Ajinkya Mohamed, Mukhtar Abdul-Mageed, Muhammad |
| contents | Speech emotion recognition (SER) is essential for enhancing human-computer interaction in speech-based applications. Despite improvements in specific emotional datasets, there is still a research gap in SER's capability to generalize across real-world situations. In this paper, we investigate approaches to generalize the SER system across different emotion datasets. In particular, we incorporate 11 emotional speech datasets and illustrate a comprehensive benchmark on the SER task. We also address the challenge of imbalanced data distribution using over-sampling methods when combining SER datasets for training. Furthermore, we explore various evaluation protocols for adeptness in the generalization of SER. Building on this, we explore the potential of Whisper for SER, emphasizing the importance of thorough evaluation. Our approach is designed to advance SER technology by integrating speaker-independent methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09933 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | What Does it Take to Generalize SER Model Across Datasets? A Comprehensive Benchmark Ibrahim, Adham Shehata, Shady Kulkarni, Ajinkya Mohamed, Mukhtar Abdul-Mageed, Muhammad Sound Artificial Intelligence Human-Computer Interaction Machine Learning Speech emotion recognition (SER) is essential for enhancing human-computer interaction in speech-based applications. Despite improvements in specific emotional datasets, there is still a research gap in SER's capability to generalize across real-world situations. In this paper, we investigate approaches to generalize the SER system across different emotion datasets. In particular, we incorporate 11 emotional speech datasets and illustrate a comprehensive benchmark on the SER task. We also address the challenge of imbalanced data distribution using over-sampling methods when combining SER datasets for training. Furthermore, we explore various evaluation protocols for adeptness in the generalization of SER. Building on this, we explore the potential of Whisper for SER, emphasizing the importance of thorough evaluation. Our approach is designed to advance SER technology by integrating speaker-independent methods. |
| title | What Does it Take to Generalize SER Model Across Datasets? A Comprehensive Benchmark |
| topic | Sound Artificial Intelligence Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2406.09933 |