HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer

Autor:	Lee, Sang-Hoon, Choi, Ha-Yeong, Oh, Hyung-Seok, Lee, Seong-Whan
Rok vydání:	2023
Předmět:	Computer Science - Sound Computer Science - Artificial Intelligence Computer Science - Multimedia Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	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/}. Comment: INTERSPEECH 2023 (Oral)
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2307.16171 Zobrazit plný text záznamu View this record from Arxiv