English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Detailed statistical analysis of call center recordings is critical in thecustomer relationship management point of view. With the recent advances inartificial intelligence, many tasks regarding the calculation of callstatistics are now performed automatically. This work proposes a neural networkframework where the aim is to correctly identify audio segments and classifythem as either customer or agent sections. Accurately identifying thesesections gives a fair metric for evaluating agents' performances. We inheritedthe convolutional recurrent neural network (CRNN) architecture commonly usedfor such problems as music genre classification. We also tested the samearchitecture's performance, where the previous class information and the genderinformation of speakers are also added to the training data labels. We saw thatCRNN could generalize the training data and perform well on validation data forthis problem with and without the gender information. Moreover, even thetraining was performed using Turkish speech samples; the trained network wasproven to achieve high accuracy for call center recordings in other languageslike German and English.

Classification of Audio Segments in Call Center Recordings using Convolutional Recurrent Neural Networks