A Multimodal Approach to Improve Performance Evaluation of Call Center Agent
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...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , , |
| منشور في: |
2021
|
| الموضوعات: | |
| الوصول للمادة أونلاين: | https://bspace.buid.ac.ae/handle/1234/3034 https://doi.org/10.3390/s21082720. |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1862980613125963776 |
|---|---|
| author | Ahmed , Abdelrahman |
| author2 | Shaalan, Khaled Toral, Sergio Hifny, Yasser |
| author2_role | author author author |
| author_facet | Ahmed , Abdelrahman Shaalan, Khaled Toral, Sergio Hifny, Yasser |
| author_role | author |
| dc.creator.none.fl_str_mv | Ahmed , Abdelrahman Shaalan, Khaled Toral, Sergio Hifny, Yasser |
| dc.date.none.fl_str_mv | 2021 2025-05-14T12:46:50Z 2025-05-14T12:46:50Z |
| dc.identifier.none.fl_str_mv | Ahmed, A. et al. (2021) “A Multimodal Approach to Improve Performance Evaluation of Call Center Agent,” Sensors (Basel, Switzerland), 21(8). 1424-8220, 1424-8220 https://bspace.buid.ac.ae/handle/1234/3034 https://doi.org/10.3390/s21082720. |
| dc.language.none.fl_str_mv | en |
| dc.publisher.none.fl_str_mv | MDPI |
| dc.relation.none.fl_str_mv | Sensors (Basel, Switzerland)v21 n8 (20210412) |
| dc.subject.none.fl_str_mv | performance modeling; multimodal classification; BiLSTM; CNNs; attention layer |
| dc.title.none.fl_str_mv | A Multimodal Approach to Improve Performance Evaluation of Call Center Agent |
| dc.type.none.fl_str_mv | Article |
| description | 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. |
| id | budr_b37fbd2d43fcf91d58c470d2bcbccfee |
| identifier_str_mv | Ahmed, A. et al. (2021) “A Multimodal Approach to Improve Performance Evaluation of Call Center Agent,” Sensors (Basel, Switzerland), 21(8). 1424-8220, 1424-8220 |
| language_invalid_str_mv | en |
| network_acronym_str | budr |
| network_name_str | The British University in Dubai repository |
| oai_identifier_str | oai:bspace.buid.ac.ae:1234/3034 |
| publishDate | 2021 |
| publisher.none.fl_str_mv | MDPI |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| spelling | A Multimodal Approach to Improve Performance Evaluation of Call Center AgentAhmed , AbdelrahmanShaalan, KhaledToral, SergioHifny, Yasserperformance modeling; multimodal classification; BiLSTM; CNNs; attention layerThe 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.MDPI2025-05-14T12:46:50Z2025-05-14T12:46:50Z2021ArticleAhmed, A. et al. (2021) “A Multimodal Approach to Improve Performance Evaluation of Call Center Agent,” Sensors (Basel, Switzerland), 21(8).1424-8220, 1424-8220https://bspace.buid.ac.ae/handle/1234/3034https://doi.org/10.3390/s21082720.enSensors (Basel, Switzerland)v21 n8 (20210412)oai:bspace.buid.ac.ae:1234/30342025-05-14T12:49:08Z |
| spellingShingle | A Multimodal Approach to Improve Performance Evaluation of Call Center Agent Ahmed , Abdelrahman performance modeling; multimodal classification; BiLSTM; CNNs; attention layer |
| title | A Multimodal Approach to Improve Performance Evaluation of Call Center Agent |
| title_full | A Multimodal Approach to Improve Performance Evaluation of Call Center Agent |
| title_fullStr | A Multimodal Approach to Improve Performance Evaluation of Call Center Agent |
| title_full_unstemmed | A Multimodal Approach to Improve Performance Evaluation of Call Center Agent |
| title_short | A Multimodal Approach to Improve Performance Evaluation of Call Center Agent |
| title_sort | A Multimodal Approach to Improve Performance Evaluation of Call Center Agent |
| topic | performance modeling; multimodal classification; BiLSTM; CNNs; attention layer |
| url | https://bspace.buid.ac.ae/handle/1234/3034 https://doi.org/10.3390/s21082720. |