Improving QoE of SIP-based automated voice interaction in mobile networks

Mobile voice-assisted services are currently experiencing strong growth. However, occasionally low real-time quality of service within mobile networks could have significant negative impact on quality of experience of users interacting with automated voice services. Latency may grow to unacceptable levels and speech recognition and synthesis might suffer. We present a methodology of mitigating such effects by monitoring the immediate connection status and adapting various parameters of the SIP communication setup (buffer size, codec) in response, thus radically improving user experience. We demonstrate practical usability by implementation and testing in a real mobile network and by performing multiple test scenarios when interacting with a state-of-the-art automated voice platform.