Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909834851385344 |
|---|---|
| author | Tiwari, Upasana Chakraborty, Rupayan Kopparapu, Sunil Kumar |
| author_facet | Tiwari, Upasana Chakraborty, Rupayan Kopparapu, Sunil Kumar |
| contents | Effectiveness of speech emotion recognition in real-world scenarios is often hindered by noisy environments and variability across datasets. This paper introduces a two-step approach to enhance the robustness and generalization of speech emotion recognition models through improved representation learning. First, our model employs EDRL (Emotion-Disentangled Representation Learning) to extract class-specific discriminative features while preserving shared similarities across emotion categories. Next, MEA (Multiblock Embedding Alignment) refines these representations by projecting them into a joint discriminative latent subspace that maximizes covariance with the original speech input. The learned EDRL-MEA embeddings are subsequently used to train an emotion classifier using clean samples from publicly available datasets, and are evaluated on unseen noisy and cross-corpus speech samples. Improved performance under these challenging conditions demonstrates the effectiveness of the proposed method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09072 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition Tiwari, Upasana Chakraborty, Rupayan Kopparapu, Sunil Kumar Sound Artificial Intelligence Human-Computer Interaction Machine Learning Audio and Speech Processing Effectiveness of speech emotion recognition in real-world scenarios is often hindered by noisy environments and variability across datasets. This paper introduces a two-step approach to enhance the robustness and generalization of speech emotion recognition models through improved representation learning. First, our model employs EDRL (Emotion-Disentangled Representation Learning) to extract class-specific discriminative features while preserving shared similarities across emotion categories. Next, MEA (Multiblock Embedding Alignment) refines these representations by projecting them into a joint discriminative latent subspace that maximizes covariance with the original speech input. The learned EDRL-MEA embeddings are subsequently used to train an emotion classifier using clean samples from publicly available datasets, and are evaluated on unseen noisy and cross-corpus speech samples. Improved performance under these challenging conditions demonstrates the effectiveness of the proposed method. |
| title | Emotion-Disentangled Embedding Alignment for Noise-Robust and Cross-Corpus Speech Emotion Recognition |
| topic | Sound Artificial Intelligence Human-Computer Interaction Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2510.09072 |