Variational Bayesian speaker diarization of meeting recordings
Variational Bayesian speaker diarization of meeting recordings
复制标题
DOI：
10.1109/icassp.2010.5495087
复制
发表时间：
2010-03
期刊：
影响因子：
--
通讯作者：
F. Valente;P. Motlícek;Deepu Vijayasenan
中科院分区：
文献类型：
--
作者：
F. Valente;P. Motlícek;Deepu Vijayasenan
本文探讨了使用变分贝叶斯（VB）框架的扬声器日记的会议数据扩展以前的相关工作广播新闻音频。VB学习的目标是最大化模型边际似然的边界（称为自由能），并允许根据相同的目标函数进行联合模型学习和模型选择。虽然BIC仅在渐近极限中有效，但自由能始终是有效的界限。本文提出了使用自由能作为说话人日志化的目标函数。它可以用于在没有任何监督或调整的情况下动态地选择通常影响日志化性能的元素，即，所推断的扬声器的数量、GMM的大小和初始化。所提出的方法相比，与传统的国家的最先进的系统上的RT06评估数据的会议录音日记，并显示出8.4%的改善相对而言的扬声器错误。
This paper investigates the use of the Variational Bayesian (VB) framework for speaker diarization of meetings data extending previous related works on Broadcast News audio. VB learning aims at maximizing a bound, known as Free Energy, on the model marginal likelihood and allows joint model learning and model selection according to the same objective function. While the BIC is valid only in the asymptotic limit, the Free Energy is always a valid bound. The paper proposes the use of Free Energy as objective function in speaker diarization. It can be used to select dynamically without any supervision or tuning, elements that typically affect the diarization performance i.e. the inferred number of speakers, the size of the GMM and the initialization. The proposed approach is compared with a conventional state-of-the-art system on the RT06 evaluation data for meeting recordings diarization and shows an improvement of 8.4% relative in terms of speaker error.