Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme
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.
Code (4)
Tasks
Speech SynthesisVoice ConversionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
FasterVoiceGrad: Faster One-step Diffusion-Based Voice Conversion with Adversarial Diffusion Conversion Distillation
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 ConversionFastVoiceGrad: One-step Diffusion-Based Voice Conversion with Adversarial Conditional Diffusion Distillation
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 ConversionCoMoSVC: Consistency Model-based Singing Voice Conversion
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 ConversionZero-shot Voice Conversion with Diffusion Transformers
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 ConversionNVC-Net: End-to-End Adversarial Voice Conversion
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