metadata
license: cc-by-nc-sa-4.0
pipeline_tag: audio-to-audio
Reference
@misc{wang2025solospeechenhancingintelligibilityquality,
title={SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline},
author={Helin Wang and Jiarui Hai and Dongchao Yang and Chen Chen and Kai Li and Junyi Peng and Thomas Thebaud and Laureano Moro Velazquez and Jesus Villalba and Najim Dehak},
year={2025},
eprint={2505.19314},
archivePrefix={arXiv},
primaryClass={eess.AS},
url={https://arxiv.org/abs/2505.19314},
}
Github repository: https://github.com/WangHelin1997/SoloSpeech
Project page: https://wanghelin1997.github.io/SoloSpeech-Demo/