System And Method For Processing Multi-Modal Communications Within A Call Center

摘要

A system and method for processing multi-modal communications is provided. A call is received into a call center via a telephone. The call includes an inquiry of incoming speech utterances from a caller. The call is assigned to an agent within the call center. Transcribed text is generated by performing automatic speech recognition on the incoming speech utterances. The transcribed text is displayed to the agent via a display. Text messages from the caller are separately received into the call center via the telephone during the call. The text messages are identified as originating from the caller of the call and displayed to the agent.

主权项

1. A system for processing multi-modal communications, comprising:
a call received into a call center via a telephone, wherein the call comprises an inquiry of incoming speech utterances from a caller; an automatic call distributor to assign the call to an agent within the call center; a speech-to-text generator to generate transcribed text by performing automatic speech recognition on the incoming speech utterances; a display to display the transcribed text to the agent; text messages separately received into the call center during the call from the caller via the telephone; a identification module to identify the text messages as originating from the caller of the call; and the display to display the text messages to the agent of the call.