# EmoSSLSphere: Multilingual Emotional Speech Synthesis with Spherical Vectors and Discrete Speech Tokens

arXiv: https://arxiv.org/abs/2508.11273 · HTML: https://mlsanity.com/paper/2508.11273/

## Key facts

- No citing papers in the map yet (data through 20 Oct 2026).
- Placed in Emotional speech synthesis and recognition, one of 11 directions in Speech and audio language models.
- First posted on arXiv 15 Aug 2025.

## Placed in

- Speech and audio language models / [Emotional speech synthesis and recognition](https://mlsanity.com/speech/emotional-speech-synthesis-and-recognition/)

## Abstract (arXiv)

This paper introduces EmoSSLSphere, a novel framework for multilingual emotional text-to-speech (TTS) synthesis that combines spherical emotion vectors with discrete token features derived from self-supervised learning (SSL). By encoding emotions in a continuous spherical coordinate space and leveraging SSL-based representations for semantic and acoustic modeling, EmoSSLSphere enables fine-grained emotional control, effective cross-lingual emotion transfer, and robust preservation of speaker identity. We evaluate EmoSSLSphere on English and Japanese corpora, demonstrating significant improvements in speech intelligibility, spectral fidelity, prosodic consistency, and overall synthesis quality. Subjective evaluations further confirm that our method outperforms baseline models in terms of naturalness and emotional expressiveness, underscoring its potential as a scalable solution for multilingual emotional TTS.