Multiview Canonical Correlation Analysis for Automatic Pathological Speech Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910620281995264 |
|---|---|
| author | Kaloga, Yacouba Sheikh, Shakeel A. Kodrasi, Ina |
| author_facet | Kaloga, Yacouba Sheikh, Shakeel A. Kodrasi, Ina |
| contents | Recently proposed automatic pathological speech detection approaches rely on spectrogram input representations or wav2vec2 embeddings. These representations may contain pathology irrelevant uncorrelated information, such as changing phonetic content or variations in speaking style across time, which can adversely affect classification performance. To address this issue, we propose to use Multiview Canonical Correlation Analysis (MCCA) on these input representations prior to automatic pathological speech detection. Our results demonstrate that unlike other dimensionality reduction techniques, the use of MCCA leads to a considerable improvement in pathological speech detection performance by eliminating uncorrelated information present in the input representations. Employing MCCA with traditional classifiers yields a comparable or higher performance than using sophisticated architectures, while preserving the representation structure and providing interpretability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17276 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multiview Canonical Correlation Analysis for Automatic Pathological Speech Detection Kaloga, Yacouba Sheikh, Shakeel A. Kodrasi, Ina Audio and Speech Processing Machine Learning Sound Recently proposed automatic pathological speech detection approaches rely on spectrogram input representations or wav2vec2 embeddings. These representations may contain pathology irrelevant uncorrelated information, such as changing phonetic content or variations in speaking style across time, which can adversely affect classification performance. To address this issue, we propose to use Multiview Canonical Correlation Analysis (MCCA) on these input representations prior to automatic pathological speech detection. Our results demonstrate that unlike other dimensionality reduction techniques, the use of MCCA leads to a considerable improvement in pathological speech detection performance by eliminating uncorrelated information present in the input representations. Employing MCCA with traditional classifiers yields a comparable or higher performance than using sophisticated architectures, while preserving the representation structure and providing interpretability. |
| title | Multiview Canonical Correlation Analysis for Automatic Pathological Speech Detection |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2409.17276 |