# SelfTTS: cross-speaker style transfer through explicit embedding disentanglement and self-refinement using self-augmentation

Source: [SelfTTS: cross-speaker style transfer through explicit embedding disentanglement and self-refinement using self-augmentation](<https://www.sota2.com/research/paper/69c21ad80636e5bf4afc4db4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-25T05:00:19.379Z

Authors: Lucas H. Ueda, Jo\\~ao G. T. Lima, Pedro R. Corr\\^ea, Fl\\'avio O. Sim\\~oes, M\\'ario U. Neto, Paula D. P. Costa

Published: 2026-03-23T17:45:03.000Z

## Abstract

This paper presents SelfTTS, a text-to-speech (TTS) model designed for cross-speaker style transfer that eliminates the need for external pre-trained speaker or emotion encoders. The architecture achieves emotional expressivity in neutral speakers through an explicit disentanglement strategy utilizing Gradient Reversal Layers (GRL) combined with cosine similarity loss to decouple speaker and emotion information. We introduce Multi Positive Contrastive Learning (MPCL) to induce clustered representations of speaker and emotion embeddings based on their respective labels. Furthermore, SelfTTS employs a self-refinement strategy via Self-Augmentation, exploiting the model's voice conversion capabilities to enhance the naturalness of synthesized speech. Experimental results demonstrate that SelfTTS achieves superior emotional naturalness (eMOS) and robust stability in target timbre and emotion compared to state-of-the-art baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Cross-speaker Style Transfer on VCTK p226](<https://www.sota2.com/research/sota/cross-speaker-style-transfer-on-vctk-p226.md>): Cross-speaker Style Transfer; VCTK p226; UTMOS: 3.3806.

- [Cross-speaker Style Transfer on VCTK p231](<https://www.sota2.com/research/sota/cross-speaker-style-transfer-on-vctk-p231.md>): Cross-speaker Style Transfer; VCTK p231; UTMOS: 3.3806.

- [Cross-speaker Style Transfer on LJSpeech](<https://www.sota2.com/research/sota/cross-speaker-style-transfer-on-ljspeech.md>): Cross-speaker Style Transfer; LJSpeech; UTMOS: 3.3951.

- [Cross-speaker style transfer on ESD (test)](<https://www.sota2.com/research/sota/cross-speaker-style-transfer-on-esd-test.md>): Cross-speaker Style Transfer; ESD (test); nMOS: 2.746.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.22252>)

[PDF](<https://arxiv.org/pdf/2603.22252.pdf>)