Interpreting Content and Speaker Characteristics in Factorised Self-Supervised Subspaces
Résumé
Self-supervised speech features encode both content and speaker information. Recent work introduced an SVD-based factorisation that decomposes these features into a shared content matrix capturing temporal variation and speaker-specific transformations capturing static speaker characteristics. However, how information is organised within these components remains unclear. In this paper, we investigate how the dimensions of WavLM-factorised content and speaker subspaces correlate with speech characteristics such as pitch, intensity, and voicing. We find that leading dimensions in the content space primarily capture intensity, higher-order formants, and voicing, while pitch is encoded in a later dimension. In contrast, the highest-variance speaker dimension is strongly associated with pitch and gender, with later dimensions capturing high-frequency variation. Intervention experiments show that manipulating these dimensions enables targeted control of speech characteristics for speech synthesis. Furthermore, modifying the content and speaker representations jointly provides fine-grained control over characteristics such as pitch and intensity.
Citer ce document
Accès au document
Texte intégral en lecture en ligne, réservé aux abonnés SPHAERO et aux membres de l'institution. Se connecter
Voir l'article sur le site de la revueAuteur(s)
Statistiques
Consultations : 2
Téléchargements : 0