@inproceedings{5540bcf3de9b46bbb61864ec2225703d,
title = "TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge",
abstract = "This paper describes the TSUP team's submission to the ISCSLP 2022 conversational short-phrase speaker diarization (CSSD) challenge which particularly focuses on short-phrase conversations with a new evaluation metric called conversational diarization error rate (CDER). In this challenge, we explore three kinds of typical speaker diarization systems, which are spectral clustering (SC) based diarization, target-speaker voice activity detection (TS-VAD) and end-to-end neural diarization (EEND) respectively. Our major findings are summarized as follows. First, the SC approach is more favored over the other two approaches under the new CDER metric. Second, tuning on hyperparameters is essential to CDER for all three types of speaker diarization systems. Specifically, CDER becomes smaller when the length of sub-segments setting longer. Finally, multi-system fusion through DOVER-LAP will worsen the CDER metric on the challenge data. Our submitted SC system eventually ranks the third place in the challenge.",
keywords = "EEND, speaker diarization, spectral clustering, TS-VAD",
author = "Bowen Pang and Huan Zhao and Gaosheng Zhang and Xiaoyue Yang and Yang Sun and Li Zhang and Qing Wang and Lei Xie",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022 ; Conference date: 11-12-2022 Through 14-12-2022",
year = "2022",
doi = "10.1109/ISCSLP57327.2022.10037846",
language = "英语",
series = "2022 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "502--506",
editor = "Lee, {Kong Aik} and Hung-yi Lee and Yanfeng Lu and Minghui Dong",
booktitle = "2022 13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022",
}