# SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations

arXiv: https://arxiv.org/abs/2606.11611 · HTML: https://mlsanity.com/paper/2606.11611/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2026.

## Built on by (most cited first, 1 of 1)

- [Phoenix TTS: High-Fidelity Synthesis and Voice Conversion via Flow-Matching-Driven Speech Tokenization](https://mlsanity.com/paper/2608.11737/) (2026)

## Abstract (arXiv)

Zero-shot text-to-speech (TTS) relies on robust speech representations. However, current speech tokenizers face a fundamental trade-off: acoustic codecs preserve high-fidelity audio but lack linguistic constraints, causing content errors during generation, whereas semantic tokens from self-supervised learning (SSL) models ensure precise text alignment but discard some acoustic information. To bridge this gap, we propose SARA, a dual-stream VAE that directly fuses a frozen SSL semantic anchor with a dedicated residual acoustic encoder. This effectively mitigates the dilemma, creating an efficient and compact latent space without relying on complex regularizers. SARA achieves superior reconstruction quality over strong baselines. Furthermore, in downstream zero-shot TTS tasks, it yields highly natural and expressive synthesis quality, and maintains robust generation performance even under accelerated inference, offering a favorable trade-off between synthesis speed and computational cost.