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 2203.06396cs.CL
收藏

呼叫中心领域语音会话分析的组合方法

A combined approach to the analysis of speech conversations in a contact center domain

University of Udine(乌迪内大学);Gap S.r.l.u.(Gap有限责任公司);University of Ferrara(费拉拉大学)

Andrea Brunello, Enrico Marzano, Angelo Montanari, Guido Sciavicco

摘要:

如今,对客户数据进行更准确的深度分析是一个非常强大的技术趋势,对私营和上市公司都很有吸引力。在联络中心领域尤其如此,语音分析是一种非常强大的方法,可以从来自客户和人工座席对话的非结构化数据中获得见解。在这项工作中,我们描述了一个实验的语音分析过程中,意大利的联络中心,处理从入站或出站流提取的通话录音。首先,我们详细说明了基于Kaldi框架的内部语音到文本解决方案的开发,并评估其性能(并将其与Google Cloud Speech API进行比较)。然后,我们评估和比较不同的方法来语义标记的通话记录,从经典的正则表达式的机器学习模型的基础上ngrams和逻辑回归,并提出了一个组合,这是提供了一致的好处。最后,一个决策树诱导器,称为J48 S,被应用到标记的问题。这样的算法本身就能够利用连续数据,如文本,用于分类目的。该解决方案与其他方法进行了比较,并显示出具有竞争力的分类性能,同时生成高度可解释的模型,并降低了数据准备阶段的复杂性。对整个过程的潜在业务影响进行了彻底审查。

英文摘要:

The ever more accurate search for deep analysis in customer data is a really strong technological trend nowadays, quite appealing to both private and public companies. This is particularly true in the contact center domain, where speech analytics is an extremely powerful methodology for gaining insights from unstructured data, coming from customer and human agent conversations. In this work, we describe an experimentation with a speech analytics process for an Italian contact center, that deals with call recordings extracted from inbound or outbound flows. First, we illustrate in detail the development of an in-house speech-to-text solution, based on Kaldi framework, and evaluate its performance (and compare it to Google Cloud Speech API). Then, we evaluate and compare different approaches to the semantic tagging of call transcripts, ranging from classic regular expressions to machine learning models based on ngrams and logistic regression, and propose a combination of them, which is shown to provide a consistent benefit. Finally, a decision tree inducer, called J48S, is applied to the problem of tagging. Such an algorithm is natively capable of exploiting sequential data, such as texts, for classification purposes. The solution is compared with the other approaches and is shown to provide competitive classification performances, while generating highly interpretable models and reducing the complexity of the data preparation phase. The potential operational impact of the whole process is thoroughly examined.

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。

↑