An Explainable Proxy Model for Multiabel Audio Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910299143012352 |
|---|---|
| author | Mariotte, Théo Almudévar, Antonio Tahon, Marie Ortega, Alfonso |
| author_facet | Mariotte, Théo Almudévar, Antonio Tahon, Marie Ortega, Alfonso |
| contents | Audio signal segmentation is a key task for automatic audio indexing. It consists of detecting the boundaries of class-homogeneous segments in the signal. In many applications, explainable AI is a vital process for transparency of decision-making with machine learning. In this paper, we propose an explainable multilabel segmentation model that solves speech activity (SAD), music (MD), noise (ND), and overlapped speech detection (OSD) simultaneously. This proxy uses the non-negative matrix factorization (NMF) to map the embedding used for the segmentation to the frequency domain. Experiments conducted on two datasets show similar performances as the pre-trained black box model while showing strong explainability features. Specifically, the frequency bins used for the decision can be easily identified at both the segment level (local explanations) and global level (class prototypes). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08268 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | An Explainable Proxy Model for Multiabel Audio Segmentation Mariotte, Théo Almudévar, Antonio Tahon, Marie Ortega, Alfonso Audio and Speech Processing Artificial Intelligence Machine Learning Sound Signal Processing Audio signal segmentation is a key task for automatic audio indexing. It consists of detecting the boundaries of class-homogeneous segments in the signal. In many applications, explainable AI is a vital process for transparency of decision-making with machine learning. In this paper, we propose an explainable multilabel segmentation model that solves speech activity (SAD), music (MD), noise (ND), and overlapped speech detection (OSD) simultaneously. This proxy uses the non-negative matrix factorization (NMF) to map the embedding used for the segmentation to the frequency domain. Experiments conducted on two datasets show similar performances as the pre-trained black box model while showing strong explainability features. Specifically, the frequency bins used for the decision can be easily identified at both the segment level (local explanations) and global level (class prototypes). |
| title | An Explainable Proxy Model for Multiabel Audio Segmentation |
| topic | Audio and Speech Processing Artificial Intelligence Machine Learning Sound Signal Processing |
| url | https://arxiv.org/abs/2401.08268 |