Speech analytics with adaptive filtering

摘要

Contact center agents often work in close proximity to other agents. As a primary agent is engaged in a call, a neighboring agent speech may be picked up by the primary agent's microphone. Contact centers using automated speech recognition systems may monitor the agent's speech for key terms and, if detected, respond accordingly. Determining a primary agent spoke a key term, when the true speaker of the key term is a neighboring agent, may cause errors or other problems. Characterizing at least the primary agent's voice and then, once a key term is detected, determining if it was the primary agent that spoke the key term, may help to reduce the errors. Additionally, computational requirements may be reduced as non-key terms may be quickly discarded and optionally, key terms determined to not have been spoke by the primary agent, may also be discarded without further processing.

主权项

1. A method, comprising:
characterizing, by a processor, a number of primary voice attributes of a primary agent; accessing, by the processor, a voice portion of a communication between the primary agent and a customer on a communications network; monitoring the voice portion of the communication for a key term; associating, by the processor, the key term with an expected time context; determining, by the processor, an actual time context of the key term within the communication; detecting, by the processor, the key term in the monitored voice portion; in response to detecting the key term, characterizing a number of term attributes for the key term; and the processor, upon determining (a) that the number of term attributes for the key term substantially matches the number of primary voice attributes and (b) that the actual time context and the expected time context substantially agree, assigning the key term speaker to be the primary agent.