Integration of speech separation, diarization, and recognition for multi-speaker meetings: Separated LibriCSS dataset

Dataset This data repository contains separated audio streams for the LibriCSS dataset using the following window-based separation methods: 1. Mask-based MVDR: Takuya Yoshioka, Hakan Erdogan, Zhuo Chen, and Fil Alleva, “Multi-microphone neural speech separation for farfield multi-talker speech recognition,” ICASSP 2018. 2. Sequential neural beamforming: Zhong-Qiu Wang, Hakan Erdogan, Scott Wisdom, Kevin Wilson, Desh Raj, Shinji Watanabe, Zhuo Chen, and John R. Hershey, “Sequential multi-frame neural beamforming for speech separation and enhancement,” IEEE SLT 2021. These audio streams were used for evaluating the diarization and ASR models in our JSALT 2020 paper. The repository contains the following archive files: libricss_mvdr_2stream.tar.gz libricss_sequential_3stream.tar.gz Citation If you use these separated audio streams in your research, consider citing: @article{Raj2020IntegrationOS,
  title={Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis},
  author={Desh Raj and Pavel Denisov and Z. Chen and H. Erdogan and Zili Huang and Mao-Kui He and Shinji Watanabe and Jun Du and T. Yoshioka and Yi Luo and N. Kanda and Jinyu Li and S. Wisdom and J. Hershey},
  journal={2021 IEEE Spoken Language Technology (SLT) Workshop},
  year={2021}
}

数据集说明：本数据仓库为LibriCSS数据集提供了基于以下窗口式音频分离方法得到的分离音频流：
1. 基于掩码的MVDR（Mask-based MVDR）：Takuya Yoshioka、Hakan Erdogan、Zhuo Chen、Fil Alleva，《面向远场多说话人语音识别的多麦克风神经语音分离》，ICASSP 2018。
2. 序列神经波束成形（Sequential neural beamforming）：Zhong-Qiu Wang、Hakan Erdogan、Scott Wisdom、Kevin Wilson、Desh Raj、Shinji Watanabe、Zhuo Chen、John R. Hershey，《用于语音分离与增强的序列多帧神经波束成形》，IEEE SLT 2021。
上述分离音频流曾用于我们在JSALT 2020会议论文中对说话人分割聚类与自动语音识别（ASR）模型的评估工作。
本仓库包含以下归档文件：libricss_mvdr_2stream.tar.gz、libricss_sequential_3stream.tar.gz。

引用说明：若您在研究中使用本分离音频流，请引用以下文献：
@article{Raj2020IntegrationOS,
title={多说话人会议场景下语音分离、说话人分割聚类与识别的融合：系统描述、对比与分析},
author={Desh Raj、Pavel Denisov、Z. Chen、Hakan Erdogan、Zili Huang、Mao-Kui He、Shinji Watanabe、Jun Du、T. Yoshioka、Yi Luo、N. Kanda、Jinyu Li、S. Wisdom、J. Hershey},
journal={2021 IEEE口语语言技术研讨会（SLT Workshop）},
year={2021}
}