# DS-Codec: Dual-Stage Training with Mirror-to-NonMirror Architecture Switching for Speech Codec

arXiv: https://arxiv.org/abs/2505.24314 · HTML: https://mlsanity.com/paper/2505.24314/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2025.

## 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)

Neural speech codecs are essential for advancing text-to-speech (TTS) systems. With the recent success of large language models in text generation, developing high-quality speech tokenizers has become increasingly important. This paper introduces DS-Codec, a novel neural speech codec featuring a dual-stage training framework with mirror and non-mirror architectures switching, designed to achieve superior speech reconstruction. We conduct extensive experiments and ablation studies to evaluate the effectiveness of our training strategy and compare the performance of the two architectures. Our results show that the mirrored structure significantly enhances the robustness of the learned codebooks, and the training strategy balances the advantages between mirrored and non-mirrored structures, leading to improved high-fidelity speech reconstruction.