Empathetic IVR

Although numerous studies have indicated that customers have become more accepting of IVR systems, there are still instances that can cause frustration, especially systems that employ sub-par voice recognition software.  Frustrated and angry users will tend to emote their feelings in their speaking voice causing an already poor voice recognition system to have more trouble understanding the customer.  This leads to a vicious cycle in which the user tends to become more frustrated while the IVR system becomes less likely to recognize menu choices and/or voice commands.  Ultimately this can lead to a very negative customer experience which can effect a company's bottom line.

Yang Liu, a computer scientist at the University of Texas at Dallas, is conducting research that could change the face of voice recognition software as we know it.  She and her graduate students have received a three-year grant from the Air Force Office of Scientific Research to investigate emotion recognition and modeling in speech processing.  Liu's research will focus on voice pitch, intonation patterns and word choice and their associations with a variety of emotions such as anger, sadness, happiness, surprise and frustration.  If successful, her research could be applied to many applications including IVR systems that could quickly recognize a frustrated user and immediately transfer him or her to a human operator.  This would lead to a better overall customer experience and likely improve customer retention.