Investigating self-supervised features for expressive, multilingual voice conversion
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909608664104960 |
|---|---|
| author | Martín-Cortinas, Álvaro Sáez-Trigueros, Daniel Beringer, Grzegorz Vallés-Pérez, Iván Barra-Chicote, Roberto Tura-Vecino, Biel Gabryś, Adam Bilinski, Piotr Merritt, Thomas Lorenzo-Trueba, Jaime |
| author_facet | Martín-Cortinas, Álvaro Sáez-Trigueros, Daniel Beringer, Grzegorz Vallés-Pérez, Iván Barra-Chicote, Roberto Tura-Vecino, Biel Gabryś, Adam Bilinski, Piotr Merritt, Thomas Lorenzo-Trueba, Jaime |
| contents | Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between different speakers using parallel data, which is expensive to produce. Unsupervised approaches are typically trained to reconstruct the input signal, which is composed of the content and the speaker information. Disentangling these components is a challenge and often leads to speaker leakage or prosodic information removal. In this paper, we explore voice conversion by leveraging the potential of self-supervised learning (SSL). A combination of the latent representations of SSL models, concatenated with speaker embeddings, is fed to a vocoder which is trained to reconstruct the input. Zero-shot voice conversion results show that this approach allows to keep the prosody and content of the source speaker while matching the speaker similarity of a VC system based on phonetic posteriorgrams (PPGs). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_08278 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Investigating self-supervised features for expressive, multilingual voice conversion Martín-Cortinas, Álvaro Sáez-Trigueros, Daniel Beringer, Grzegorz Vallés-Pérez, Iván Barra-Chicote, Roberto Tura-Vecino, Biel Gabryś, Adam Bilinski, Piotr Merritt, Thomas Lorenzo-Trueba, Jaime Audio and Speech Processing Voice conversion (VC) systems are widely used for several applications, from speaker anonymisation to personalised speech synthesis. Supervised approaches learn a mapping between different speakers using parallel data, which is expensive to produce. Unsupervised approaches are typically trained to reconstruct the input signal, which is composed of the content and the speaker information. Disentangling these components is a challenge and often leads to speaker leakage or prosodic information removal. In this paper, we explore voice conversion by leveraging the potential of self-supervised learning (SSL). A combination of the latent representations of SSL models, concatenated with speaker embeddings, is fed to a vocoder which is trained to reconstruct the input. Zero-shot voice conversion results show that this approach allows to keep the prosody and content of the source speaker while matching the speaker similarity of a VC system based on phonetic posteriorgrams (PPGs). |
| title | Investigating self-supervised features for expressive, multilingual voice conversion |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.08278 |