Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning
원문 초록
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and pre-known speakers. However, zero-shot voice style transfer, which learns from non-parallel data and generates voices for previously unseen speakers, remains a challenging problem. We propose a novel zero-shot voice transfer method via disentangled representation learning. The proposed method first encodes speaker-related style and voice content of each input voice into separated low-dimensional embedding spaces, and then transfers to a new voice by combining the source content embedding and target style embedding through a decoder. With information-theoretic guidance, the style and content embedding spaces are representative and (ideally) independent of each other. On real-world VCTK datasets, our method outperforms other baselines and obtains state-of-the-art results in terms of transfer accuracy and voice naturalness for voice style transfer experiments under both many-to-many and zero-shot setups.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Riemannian generative decoder
Boosting Team Modeling through Tempo-Relational Representation Learning
Representation Learning through Multimodal Attention and Time-Sync Comments for Affective Video Content Analysis
SAR Image Despeckling Using Continuous Attention Module
Learning to Represent the Evolution of Dynamic Graphs with Recurrent Models
Making Language Model a Hierarchical Classifier and Generator
토론
이 논문과 연결된 포럼 글이 아직 없습니다.