Patent attributes
Various embodiments of the invention provide methods, systems, and computer program products for handling poor voice quality being experienced by a remote party on a call. In various embodiments, an assessment is received from the party at an IVR on the voice quality of the call. Accordingly, data is collected for one or more parameters associated with at least one of audio of the call and a network used to carry the audio of the call in response to the party experiencing poor voice quality. At this point, a predictive model is used to predict at least one cause for the poor voice quality. Here, the data collected for the one or more parameters is provided as input to the predictive model. Accordingly, one or more actions are taken to attempt to address the at least one cause and improve the voice quality on the call for the remote party.