Y.Fan,  J.W.Kang,  L.T.Li,  K.C.Li,  H.L.Chen,  S.T.Cheng,  P.Y.Zhang,  Z.Y.Zhou,  Y.Q.Cai,  D.Wang*

@inproceedings{fan2020cn,
 title={Cn-celeb: a challenging chinese speaker recognition dataset}, 
author={Fan, Yue and Kang, JW and Li, LT and Li, KC and Chen, HL and Cheng, ST and Zhang, PY and Zhou, ZY and Cai, YQ and Wang, Dong},
 booktitle={ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
 pages={7604--7608}, year={2020}, organization={IEEE} }
            

Recently, researchers set an ambitious goal of conducting speaker recognition in unconstrained conditions where the variations on ambient, channel and emotion could be arbitrary. However, most publicly available datasets are collected under constrained environments, i.e., with little noise and limited channel variation. These datasets tend to deliver over-optimistic performance and do not meet the request of research on speaker recognition in unconstrained conditions. In this paper, we present CN-Celeb, a large-scale speaker recognition dataset collected ‘in the wild’. This dataset contains more than 130, 000 utterances from 1, 000 Chinese celebrities, and covers 11 different genres in real world. Experiments conducted with two state-of-the-art speaker recognition approaches (i-vector and x-vector) show that the performance on CN-Celeb is far inferior to the one obtained on VoxCeleb, a widely used speaker recognition dataset. This result demonstrates that in real-life conditions, the performance of existing techniques might be much worse than it was thought. Our database is free for researchers and can be downloaded from http://project.cslt.org.

L.T.Li,  R.Q.Liu,  J.W.Kang,  Y.Fan,  H.Cui,  Y.Q.Cai,  R.Vipperla,  T.F.Zheng,  D.Wang*

@article{li2022cn,
  title={CN-Celeb: multi-genre speaker recognition},
  author={Li, Lantian and Liu, Ruiqi and Kang, Jiawen and Fan, Yue and Cui, Hao and Cai, Yunqi and Vipperla, Ravichander and Zheng, Thomas Fang and Wang, Dong},
  journal={Speech Communication},
  year={2022},
  publisher={Elsevier}
}
            

Research on speaker recognition is extending to address the vulnerability in the wild conditions, among which genre mismatch is perhaps the most challenging, for instance, enrollment with reading speech while testing with conversational or singing audio. This mismatch leads to complex and composite inter-session variations, both intrinsic (i.e., speaking style, physiological status) and extrinsic (i.e., recording device, background noise). Unfortunately, the few existing multi-genre corpora are not only limited in size but are also recorded under controlled conditions, which cannot support conclusive research on the multi-genre problem. In this work, we firstly publish CN-Celeb, a large-scale multi-genre corpus that includes in-the-wild speech utterances of 3,000 speakers in 11 different genres. Secondly, using this dataset, we conduct a comprehensive study on the multi-genre phenomenon, in particular the impact of the multi-genre challenge on speaker recognition and the performance gain when the new dataset is used to conduct multi-genre training.