Integrated Cognitive Solution for Call Centre Digital Transformation
How i-Con integrated with Azure cognitive services to enhance call centre customer satisfaction using speaker recognition, speech-to-text, and OCR to transform telephonic interactions into structured data.
Cognitive services can rapidly understand a caller's emotional state, share it with a listening agent, and suggest better approaches to move the customer from a negative state into a more positive one. For call centres, the ability to capture and act on this information in real time is transformative.
The Scenario
A customer service call can quickly go from bad to worse if the wrong answers are given. Being able to track client information, capture correct data, and produce accurate information in real time presents significant challenges. In this case, we explore how i-Con integrated with Azure cognitive services to enhance call centre customer satisfaction and daily operations for a leading South African call centre.
“Once we did our research and understood the need, being able to add the Azure components to i-Con was simple.”
Juan Araujo, CEO at ProSolutions Integration
Speaker Recognition
Speaker recognition accurately determines a speaker's identity based on their unique voice characteristics, streamlining the verification process and delivering a better customer experience. i-Con's speaker recognition component determined whether the customer or the agent was conducting the conversation. Separating voice allowed the system to transform data into a normalised structure for deeper analysis.
Speech Recognition
Today's speech recognition technology excels at transcribing voice with high accuracy, even in noisy telephony environments. i-Con's Speech Recognition component received audio files from an SFTP server continuously polled for new files. By processing the audio, the component generates text files with all words from the call, which are then inserted into a SQL Server database for analysis.
“Leveraging Azure, the pre-built i-Con component was able to identify proper nouns in the speech.”
Juan Araujo, CEO at ProSolutions Integration
OCR (Optical Character Recognition)
Modern AI-powered OCR solutions fuse document authenticity checks with Intelligent Character Recognition for format and semantic analysis. i-Con provided a solution to read BEE certificate content, extract specific fields, and insert them into a database linked to client accounts processed in real-time from an SFTP server and converted into a normalised format.
The Conclusion
Call centre systems using cognitive services can recognise the sentiment behind a caller's words in real-time and help agents respond more effectively. An organisation's ability to convert upset customers into neutral or happy customers during a call is key to better customer retention and reduced churn.
“i-Con's low-code approach coupled with the product's versatility makes it simple, fast, and easy to utilise any cognitive service.”
Armando Homann, Technical Director at ProSolutions Integration
