Advancing speaker embedding learning: Wespeaker toolkit for research and production

Shuai Wang, Zhengyang Chen, Bing Han, Hongji Wang, Chengdong Liang, Binbin Zhang, Xu Xiang, Wen Ding, Johan Rohdin, Anna Silnova, Yanmin Qian, Haizhou Li

Abstract

Highlights•Lightweight and Efficient Design for Both Research and Production•Extensive Models and Structured Recipes on Different Datasets•Scalable Data Management with Flexible Unified I/O Design•Cross-Platform Deployment For PCs and On-device Chips•Off-the-shelf Pretrained Models and User-Friendly Interface
BibTeX
@article{wang2024advancing,
  author = {Shuai Wang and Zhengyang Chen and Bing Han and Hongji Wang and Chengdong Liang and Binbin Zhang and Xu Xiang and Wen Ding and Johan Rohdin and Anna Silnova and Yanmin Qian and Haizhou Li},
  title = {{Advancing speaker embedding learning: Wespeaker toolkit for research and production}},
  journal = {Speech Commun.},
  year = {2024},
  doi = {10.1016/j.specom.2024.103104},
}

Loading related content...

Figure