paper-with-me

홈 › Papers

Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme

2021-09-28 · ICLR 2022 4 · Vadim Popov, Ivan Vovk, Vladimir Gogoryan, Tasnima Sadekova, Mikhail Kudinov, Jiansheng Wei

Voice conversion is a common speech synthesis task which can be solved in different ways depending on a particular real-world scenario. The most challenging one often referred to as one-shot many-to-many voice conversion consists in copying the target voice from only one reference utterance in the most general case when both source and target speakers do not belong to the training dataset. We present a scalable high-quality solution based on diffusion probabilistic modeling and demonstrate its superior quality compared to state-of-the-art one-shot voice conversion approaches. Moreover, focusing on real-time applications, we investigate general principles which can make diffusion models faster while keeping synthesis quality at a high level. As a result, we develop a novel Stochastic Differential Equations solver suitable for various diffusion model types and generative tasks as shown through empirical studies and justify it by theoretical analysis.

📄 PDF Abstract BibTeX arXiv:2109.13821

Code (4)

huawei-noah/Speech-Backbones 공식 구현 pytorch
huawei-noah/Speech-Backbones/tree/main/Grad-TTS pytorch
playvoice/grad-svc pytorch
trinhtuanvubk/diff-vc pytorch

Tasks

Speech SynthesisVoice Conversion

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation

2025-08-25 · Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo arxiv

A diffusion-based voice conversion (VC) model (e.g., VoiceGrad) can achieve high speech quality and speaker similarity; however, its conversion process is slow owing to iterative sampling. FastVoiceGrad overcomes this li…

Voice Conversion

FastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation

2024-09-03 · Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Yuto Kondo

Diffusion-based voice conversion (VC) techniques such as VoiceGrad have attracted interest because of their high VC performance in terms of speech quality and speaker similarity. However, a notable limitation is the slow…

Voice Conversion

CoMoSVC: Consistency Model-based Singing Voice Conversion

2024-01-03 · Yiwen Lu, Zhen Ye, Wei Xue, Xu Tan 외

The diffusion-based Singing Voice Conversion (SVC) methods have achieved remarkable performances, producing natural audios with high similarity to the target timbre. However, the iterative sampling process results in slo…

GPUmodelVoice Conversion

Zero-shot Voice Conversion with Diffusion Transformers

2024-11-15 · Songting Liu

Zero-shot voice conversion aims to transform a source speech utterance to match the timbre of a reference speech from an unseen speaker. Traditional approaches struggle with timbre leakage, insufficient timbre representa…

In-Context LearningVoice Conversion

NVC-Net: End-to-End Adversarial Voice Conversion

2021-06-02 · Bac Nguyen, Fabien Cardinaux

Voice conversion has gained increasing popularity in many applications of speech synthesis. The idea is to change the voice identity from one speaker into another while keeping the linguistic content unchanged. Many voic…

GPUSpeech SynthesisVoice Conversion