The paper proposes three modeling techniques to improve the performance evaluation of the call center agent. The first technique is speech processing supported by an attention layer for the agent’s recorded calls. The speech comprises 65 features for the ultimate determination of the context of the call using the Open-Smile toolkit. The second technique uses the Max Weights Similarity (MWS) approach instead of the Softmax function in the attention layer to improve the classification accuracy. MWS function replaces the Softmax function for fine-tuning the output of the attention layer for processing text. It is formed by determining the similarity in the distance of input weights of the attention layer to the weights of the max vectors. The third technique combines the agent’s recorded call speech with the corresponding transcribed text for binary classification. The speech modeling and text modeling are based on combinations of the Convolutional Neural Networks (CNNs) and Bi-directional Long-Short Term Memory (BiLSTMs). In this paper, the classification results for each model (text versus speech) are proposed and compared with the multimodal approach’s results. The multimodal classification provided an improvement of (0.22%) compared with acoustic model and (1.7%) compared with text model.
Every contact centre engages in some form of Call Quality Monitoring in order to improve agent performance and customer satisfaction. Call centres have traditionally used a manual process to sort, select, and analyse a representative sample of interactions for evaluation purposes. Unfortunately, such a process is marked by subjectivity, which in turn results in a distorted picture of agent performance. To address the challenge of identifying and removing subjectivity, empirical research is required. In this paper, we introduce an evidence-based, machine learning-driven framework for the automatic detection of subjective calls. We analyse a corpus of seven hours of recorded calls from a real-estate call centre using Deep Neural Network (DNN) for a multi-classification problem. The study establishes the first baseline for subjectivity detection, with an accuracy of 75%, which is comparable to relevant speech studies in emotional recognition and performance classification. We conclude, among other things, that in order to achieve the best performance evaluation, subjective calls should be removed from the evaluation process or subjective scores deducted from the overall results.
Measuring the productivity of an agent in a call center domain is a challenging task. Subjective measures are commonly used for evaluation in the current systems. In this paper, we propose an objective framework for modeling agent productivity for real estate call centers based on speech signal processing. The problem is formulated as a binary classification task using deep learning methods. We explore several designs for the classifier based on convolutional neural networks (CNNs), long-short-term memory networks (LSTMs), and an attention layer. The corpus consists of seven hours collected and annotated from three different call centers. The result shows that the speech-based approach can lead to significant improvements (1.57% absolute improvements) over a robust text baseline system.