End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916189977968640 |
|---|---|
| author | Kang, Wonjune Hasegawa-Johnson, Mark Roy, Deb |
| author_facet | Kang, Wonjune Hasegawa-Johnson, Mark Roy, Deb |
| contents | Zero-shot voice conversion is becoming an increasingly popular research topic, as it promises the ability to transform speech to sound like any speaker. However, relatively little work has been done on end-to-end methods for this task, which are appealing because they remove the need for a separate vocoder to generate audio from intermediate features. In this work, we propose LVC-VC, an end-to-end zero-shot voice conversion model that uses location-variable convolutions (LVCs) to jointly model the conversion and speech synthesis processes. LVC-VC utilizes carefully designed input features that have disentangled content and speaker information, and it uses a neural vocoder-like architecture that utilizes LVCs to efficiently combine them and perform voice conversion while directly synthesizing time domain audio. Experiments show that our model achieves especially well balanced performance between voice style transfer and speech intelligibility compared to several baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2205_09784 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions Kang, Wonjune Hasegawa-Johnson, Mark Roy, Deb Audio and Speech Processing Sound Zero-shot voice conversion is becoming an increasingly popular research topic, as it promises the ability to transform speech to sound like any speaker. However, relatively little work has been done on end-to-end methods for this task, which are appealing because they remove the need for a separate vocoder to generate audio from intermediate features. In this work, we propose LVC-VC, an end-to-end zero-shot voice conversion model that uses location-variable convolutions (LVCs) to jointly model the conversion and speech synthesis processes. LVC-VC utilizes carefully designed input features that have disentangled content and speaker information, and it uses a neural vocoder-like architecture that utilizes LVCs to efficiently combine them and perform voice conversion while directly synthesizing time domain audio. Experiments show that our model achieves especially well balanced performance between voice style transfer and speech intelligibility compared to several baselines. |
| title | End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2205.09784 |