SDAIMMASJul 30, 2023

HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer

arXiv:2307.16171v115 citationsh-index: 17
Originality Incremental advance
AI Analysis

This work addresses the challenge of adapting voice styles for new speakers in speech processing, representing an incremental improvement in the field.

The paper tackles the problem of zero-shot voice style transfer for novel speakers without text transcripts, achieving superior performance compared to existing models.

Despite rapid progress in the voice style transfer (VST) field, recent zero-shot VST systems still lack the ability to transfer the voice style of a novel speaker. In this paper, we present HierVST, a hierarchical adaptive end-to-end zero-shot VST model. Without any text transcripts, we only use the speech dataset to train the model by utilizing hierarchical variational inference and self-supervised representation. In addition, we adopt a hierarchical adaptive generator that generates the pitch representation and waveform audio sequentially. Moreover, we utilize unconditional generation to improve the speaker-relative acoustic capacity in the acoustic representation. With a hierarchical adaptive structure, the model can adapt to a novel voice style and convert speech progressively. The experimental results demonstrate that our method outperforms other VST models in zero-shot VST scenarios. Audio samples are available at \url{https://hiervst.github.io/}.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes