arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.11356eess.AS
收藏

第二届DIHARD语音日记挑战赛的BUT系统

BUT System for the Second DIHARD Speech Diarization Challenge

Federico Landini, Shuai Wang, Mireia Diez, Lukáš Burget, Pavel Matějka, Kateřina Žmolíková, Ladislav Mošner, Anna Silnova, Oldřich Plchot, Ondřej Novotný, Hosse… 展开作者

Federico Landini, Shuai Wang, Mireia Diez, Lukáš Burget, Pavel Matějka, Kateřina Žmolíková, Ladislav Mošner, Anna Silnova, Oldřich Plchot, Ondřej Novotný, Hossein Zeinali, Johan Rohdin

摘要:

本文介绍了获奖的系统开发的BUT团队的四个轨道的第二DIHARD语音日记挑战。对于轨道1和轨道2,系统主要基于执行x向量的凝聚层次聚类(AHC),其次是基于贝叶斯隐马尔可夫模型和变分贝叶斯推理的另一个x向量聚类。我们提供了每个步骤的改进的比较,并分享了系统核心的实现。对于来自第五次CHiME挑战赛的录音的轨道3和4,我们探索了进行多通道日志化的不同方法,并且当将AHC应用于每通道概率线性判别分析分数的融合时,获得了我们的最佳性能。

英文摘要:

This paper describes the winning systems developed by the BUT team for the four tracks of the Second DIHARD Speech Diarization Challenge. For tracks 1 and 2 the systems were mainly based on performing agglomerative hierarchical clustering (AHC) of x-vectors, followed by another x-vector clustering based on Bayes hidden Markov model and variational Bayes inference. We provide a comparison of the improvement given by each step and share the implementation of the core of the system. For tracks 3 and 4 with recordings from the Fifth CHiME Challenge, we explored different approaches for doing multi-channel diarization and our best performance was obtained when applying AHC on the fusion of per channel probabilistic linear discriminant analysis scores.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑