arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.06524eess.AScs.LGcs.SD
收藏

通过无限高斯混合模型的深度展开实现基于神经和聚类的日志化的紧密集成

Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model

NTT Corporation(日本电报电话公司)

Keisuke Kinoshita, Marc Delcroix, Tomoharu Iwata

摘要:

发言人日记作为会议分析的一项重要核心任务得到了广泛的研究。最近的趋势表明,基于端到端神经(EEND)和聚类的日志的集成是一种很有前途的方法来处理包含重叠语音的现实会话数据与任意大量的扬声器,并在各种任务上取得了最先进的结果。然而,到目前为止提出的方法还没有实现{ \it紧密}集成,因为其中采用的聚类对于聚类由EEND模块估计的说话人嵌入在任何意义上都不是最优的。为了解决这个问题,本文引入了{ \it可训练}聚类算法的集成框架,通过深入展开的非参数贝叶斯模型称为无限高斯混合模型(iGMM)。具体而言,在训练期间优化说话人嵌入,使得它更好地适合iGMM聚类,基于基于调整的兰德指数(ARI)的新聚类损失。基于CALLHOME数据的实验结果表明,与传统方法相比,该方法在区分错误率(DER)方面具有更好的性能,尤其是大大降低了说话人混淆错误,体现了iGMM融合的有效性.

英文摘要:

Speaker diarization has been investigated extensively as an important central task for meeting analysis. Recent trend shows that integration of end-to-end neural (EEND)-and clustering-based diarization is a promising approach to handle realistic conversational data containing overlapped speech with an arbitrarily large number of speakers, and achieved state-of-the-art results on various tasks. However, the approaches proposed so far have not realized {\it tight} integration yet, because the clustering employed therein was not optimal in any sense for clustering the speaker embeddings estimated by the EEND module. To address this problem, this paper introduces a {\it trainable} clustering algorithm into the integration framework, by deep-unfolding a non-parametric Bayesian model called the infinite Gaussian mixture model (iGMM). Specifically, the speaker embeddings are optimized during training such that it better fits iGMM clustering, based on a novel clustering loss based on Adjusted Rand Index (ARI). Experimental results based on CALLHOME data show that the proposed approach outperforms the conventional approach in terms of diarization error rate (DER), especially by substantially reducing speaker confusion errors, that indeed reflects the effectiveness of the proposed iGMM integration.

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。

↑