LCM-SVC: Latent Diffusion Model Based Singing Voice Conversion with Inference Acceleration via Latent Consistency Distillation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Shihao, Gu, Yu, Cui, Jianwei, Zhang, Jie, Chen, Rilin, Dai, Lirong
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914920806744064
author Chen, Shihao
Gu, Yu
Cui, Jianwei
Zhang, Jie
Chen, Rilin
Dai, Lirong
author_facet Chen, Shihao
Gu, Yu
Cui, Jianwei
Zhang, Jie
Chen, Rilin
Dai, Lirong
contents Any-to-any singing voice conversion (SVC) aims to transfer a target singer's timbre to other songs using a short voice sample. However many diffusion model based any-to-any SVC methods, which have achieved impressive results, usually suffered from low efficiency caused by a mass of inference steps. In this paper, we propose LCM-SVC, a latent consistency distillation (LCD) based latent diffusion model (LDM) to accelerate inference speed. We achieved one-step or few-step inference while maintaining the high performance by distilling a pre-trained LDM based SVC model, which had the advantages of timbre decoupling and sound quality. Experimental results show that our proposed method can significantly reduce the inference time and largely preserve the sound quality and timbre similarity comparing with other state-of-the-art SVC models. Audio samples are available at https://sounddemos.github.io/lcm-svc.
format Preprint
id arxiv_https___arxiv_org_abs_2408_12354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LCM-SVC: Latent Diffusion Model Based Singing Voice Conversion with Inference Acceleration via Latent Consistency Distillation
Chen, Shihao
Gu, Yu
Cui, Jianwei
Zhang, Jie
Chen, Rilin
Dai, Lirong
Audio and Speech Processing
Sound
Any-to-any singing voice conversion (SVC) aims to transfer a target singer's timbre to other songs using a short voice sample. However many diffusion model based any-to-any SVC methods, which have achieved impressive results, usually suffered from low efficiency caused by a mass of inference steps. In this paper, we propose LCM-SVC, a latent consistency distillation (LCD) based latent diffusion model (LDM) to accelerate inference speed. We achieved one-step or few-step inference while maintaining the high performance by distilling a pre-trained LDM based SVC model, which had the advantages of timbre decoupling and sound quality. Experimental results show that our proposed method can significantly reduce the inference time and largely preserve the sound quality and timbre similarity comparing with other state-of-the-art SVC models. Audio samples are available at https://sounddemos.github.io/lcm-svc.
title LCM-SVC: Latent Diffusion Model Based Singing Voice Conversion with Inference Acceleration via Latent Consistency Distillation
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2408.12354