---
language: en
tags:
- audio
- speech-processing
- speech-codec
- low-bitrate
- streaming
- tts
- cross-modal
license: apache-2.0
---

# SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec

## Resources
- [📄 Research Paper](https://arxiv.org/abs/2508.02849)
- [💻 Source Code](https://github.com/QiangChunyu/SecoustiCodec)
- [🤗 Demo Page](https://qiangchunyu.github.io/SecoustiCodec_Page/)

## Model Overview

SecoustiCodec is a **low-bitrate streaming speech codec** that achieves good performance in speech reconstruction at ultra-low bitrates (0.27-1 kbps). The model introduces several innovations:

- 🧠 **Cross-modal alignment**: Aligns text and speech in joint multimodal frame-level space
- 🔍 **Semantic-paralinguistic disentanglement**: Separates linguistic content from speaker characteristics
- ⚡ **Streaming support**: Real-time processing capabilities
- 📊 **Efficient quantization**: VAE+FSQ approach solves token distribution problems



## Architecture Overview

![Model Architecture](https://qiangchunyu.github.io/SecoustiCodec_Page/model.png)


## Acknowledgments
- We used [HiFiGAN](https://github.com/jik876/hifi-gan) for efficient waveform generation
- We referred to [MIMICodec](https://huggingface.co/kyutai/mimi) to implement this.


## Citation
```bibtex
@article{qiang2025secousticodec,
  title={SecoustiCodec: Cross-Modal Aligned Streaming Single-Codecbook Speech Codec},
  author={Chunyu Qiang, Haoyu Wang, Cheng Gong, Tianrui Wang, Ruibo Fu, Tao Wang, Ruilong Chen, Jiangyan Yi, Zhengqi Wen, Chen Zhang, Longbiao Wang, Jianwu Dang, Jianhua Tao},
  journal={arXiv preprint arXiv:2508.02849},
  year={2025}
}
```