2024/11/04 by Yu Pan, Pan, Yu, Yuguang Yang +7
Computer Science · #Artificial Intelligence (cs.AI) #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Natural Language Processing Techniques #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2411.02026
openalex publication_date 2024/11/04 · openalex created_date 2024/11/14 · openalex updated_date 2026/07/28
Despite recent advances in zero-shot voice conversion (VC), achieving speaker similarity and naturalness comparable to ground-truth recordings remains a significant challenge. In this letter, we propose CTEFM-VC, a zero-shot VC framework that integrates content-aware timbre ensemble modeling with conditional flow matching. Specifically, CTEFM-VC decouples utterances into content and timbre representations and leverages a conditional flow matching model to reconstruct the Mel-spectrogram of the source speech. To enhance its timbre modeling capability and naturalness of generated speech, we first introduce a context-aware timbre ensemble modeling approach that adaptively integrates diverse speaker verification embeddings and enables the effective utilization of source content and target timbre elements through a cross-attention module. Furthermore, a structural similarity-based timbre loss is presented to jointly train CTEFM-VC end-to-end. Experiments show that CTEFM-VC consistently achieves the best performance in all metrics assessing speaker similarity, speech naturalness, and intelligibility, significantly outperforming state-of-the-art zero-shot VC systems.