Wednesday, 7 March 2018

Speech analytics will improve quality by 95%

Contact Centers have thousands of valuable data bytes stashed away as call recordings. Unfortunately it takes trained personnel 3.5 minutes to just listen to a 2 minute call for just keyword detection. Natural Language Processing (NLP) combines with Machine learning to to analyse every single call in minutes. The use cases for this are unlimited. But an immediate application will be seen in quality.

Currently Quality assurance teams can go through about only about 5% of the total recordings. Speech analytics can go through every single recording— making the process 95% more accurate.

Ozonetel’s Speech analytics system is already in use. Clients are using the system to get real time feedback on 4 parameters: greeting detection, agent quality, phrase detection and customer response.  The system is 15x faster that a QA team in judging these basic parameters, giving real time feedback to the agent and improving quality drastically.