Stylebook: Content-Dependent Speaking Style Modeling for Any-to-Any Voice Conversion using Only Speech Data

TL;DR

This paper introduces Stylebook, a novel voice conversion method that uses a self-supervised learning model and style embeddings to accurately transfer speaking styles without text or speaker labels, improving speaker similarity.

Contribution

It presents a new style extraction and transfer approach using stylebook embeddings and attention mechanisms, enhancing style fidelity in any-to-any voice conversion.

Findings

Achieves better speaker similarity than baseline models.

Effectively captures and transfers rich speaking styles.

Maintains computational efficiency with longer utterances.

Abstract

While many recent any-to-any voice conversion models succeed in transferring some target speech's style information to the converted speech, they still lack the ability to faithfully reproduce the speaking style of the target speaker. In this work, we propose a novel method to extract rich style information from target utterances and to efficiently transfer it to source speech content without requiring text transcriptions or speaker labeling. Our proposed approach introduces an attention mechanism utilizing a self-supervised learning (SSL) model to collect the speaking styles of a target speaker each corresponding to the different phonetic content. The styles are represented with a set of embeddings called stylebook. In the next step, the stylebook is attended with the source speech's phonetic content to determine the final target style for each source content. Finally, content information extracted from the source speech and content-dependent target style embeddings are fed into a diffusion-based decoder to generate the converted speech mel-spectrogram. Experiment results show that our proposed method combined with a diffusion-based generative model can achieve better speaker similarity in any-to-any voice conversion tasks when compared to baseline models, while the increase in computational complexity with longer utterances is suppressed.