Abstract: A device initiates voice communication sessions with a media resource function processor (MRFP) of a network, where each voice communication session communicates audio data via one or more network devices of the network. For each voice communication session, the device sends first audio data to the MRFP and receives second audio data from the MRFP via the voice communication session, processes the first audio data and second audio data to determine one or more characteristics of the second audio data, and generates a record concerning the voice communication session based on the one or more characteristics of the second audio data. The device generates a report based on a respective record of each voice communication session, processes the report using an artificial intelligence technique to identify an issue concerning at least one network device, and performs, based on identifying the issue, an action concerning the at least one network device.