Disentangling Pitch and Creak for Speaker Identity Preservation in Speech Synthesis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908836236886016 |
|---|---|
| author | Rautenberg, Frederik Wiechmann, Jana Wagner, Petra Haeb-Umbach, Reinhold |
| author_facet | Rautenberg, Frederik Wiechmann, Jana Wagner, Petra Haeb-Umbach, Reinhold |
| contents | We introduce a system capable of faithfully modifying the perceptual voice quality of creak while preserving the speaker's perceived identity. While it is well known that high creak probability is typically correlated with low pitch, it is important to note that this is a property observed on a population of speakers but does not necessarily hold across all situations. Disentanglement of pitch from creak is achieved by augmentation of the training dataset of a speech synthesis system with a speaker manipulation block based on conditional continuous normalizing flow. The experiments show greatly improved speaker verification performance over a range of creak manipulation strengths. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14686 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Disentangling Pitch and Creak for Speaker Identity Preservation in Speech Synthesis Rautenberg, Frederik Wiechmann, Jana Wagner, Petra Haeb-Umbach, Reinhold Audio and Speech Processing We introduce a system capable of faithfully modifying the perceptual voice quality of creak while preserving the speaker's perceived identity. While it is well known that high creak probability is typically correlated with low pitch, it is important to note that this is a property observed on a population of speakers but does not necessarily hold across all situations. Disentanglement of pitch from creak is achieved by augmentation of the training dataset of a speech synthesis system with a speaker manipulation block based on conditional continuous normalizing flow. The experiments show greatly improved speaker verification performance over a range of creak manipulation strengths. |
| title | Disentangling Pitch and Creak for Speaker Identity Preservation in Speech Synthesis |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2602.14686 |