Dirichlet process mixture model based on topologically augmented signal representation for clustering infant vocalizations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910589884825600 |
|---|---|
| author | Bonafos, Guillem Bourot, Clara Pudlo, Pierre Freyermuth, Jean-Marc Reboul, Laurence Tronçon, Samuel Rey, Arnaud |
| author_facet | Bonafos, Guillem Bourot, Clara Pudlo, Pierre Freyermuth, Jean-Marc Reboul, Laurence Tronçon, Samuel Rey, Arnaud |
| contents | Based on audio recordings made once a month during the first 12 months of a child's life, we propose a new method for clustering this set of vocalizations. We use a topologically augmented representation of the vocalizations, employing two persistence diagrams for each vocalization: one computed on the surface of its spectrogram and one on the Takens' embeddings of the vocalization. A synthetic persistent variable is derived for each diagram and added to the MFCCs (Mel-frequency cepstral coefficients). Using this representation, we fit a non-parametric Bayesian mixture model with a Dirichlet process prior to model the number of components. This procedure leads to a novel data-driven categorization of vocal productions. Our findings reveal the presence of 8 clusters of vocalizations, allowing us to compare their temporal distribution and acoustic profiles in the first 12 months of life. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05760 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dirichlet process mixture model based on topologically augmented signal representation for clustering infant vocalizations Bonafos, Guillem Bourot, Clara Pudlo, Pierre Freyermuth, Jean-Marc Reboul, Laurence Tronçon, Samuel Rey, Arnaud Applications Sound Audio and Speech Processing Machine Learning Based on audio recordings made once a month during the first 12 months of a child's life, we propose a new method for clustering this set of vocalizations. We use a topologically augmented representation of the vocalizations, employing two persistence diagrams for each vocalization: one computed on the surface of its spectrogram and one on the Takens' embeddings of the vocalization. A synthetic persistent variable is derived for each diagram and added to the MFCCs (Mel-frequency cepstral coefficients). Using this representation, we fit a non-parametric Bayesian mixture model with a Dirichlet process prior to model the number of components. This procedure leads to a novel data-driven categorization of vocal productions. Our findings reveal the presence of 8 clusters of vocalizations, allowing us to compare their temporal distribution and acoustic profiles in the first 12 months of life. |
| title | Dirichlet process mixture model based on topologically augmented signal representation for clustering infant vocalizations |
| topic | Applications Sound Audio and Speech Processing Machine Learning |
| url | https://arxiv.org/abs/2407.05760 |