Techniques are described herein for caller acoustic properties extraction by sampling an initial duration of the connected Real-time Transport Protocol (RTP) caller stream and analyzing a received transcript of the ongoing live stream. A Speech Synthesis Markup Language (SSML) mapping of the caller acoustic information is generated in the most suitable customer-understandable format. These techniques may provide automated identification and enable Push To Answer when the caller is not able to understand what is being communicated by the agent.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.