Dirichlet process mixture model based on topologically augmented signal representation for clustering infant vocalizations - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2024

Dirichlet process mixture model based on topologically augmented signal representation for clustering infant vocalizations

Résumé

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.
Fichier principal
Vignette du fichier
Interspeech2024.pdf (318.44 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04638275 , version 1 (08-07-2024)

Licence

Identifiants

  • HAL Id : hal-04638275 , version 1

Citer

Guillem Bonafos, Clara Bourot, Pierre Pudlo, Jean-Marc Freyermuth, Laurence Reboul, et al.. Dirichlet process mixture model based on topologically augmented signal representation for clustering infant vocalizations. 2024. ⟨hal-04638275⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More