Abstract: Generally discussed herein are devices, systems, and methods for virtual agent selection of an option not expressly selected by a user. A method can include receiving, from a virtual agent interface device of the virtual agent device, a response regarding a problem, wherein the response is responsive to a prompt, and wherein the prompt is associated with one or more expected responses, determining whether the response is a match to one of the expected answers by performing one or more of (a) an ordinal match, (b) an inclusive match, (c) an entity match, and (d) a model match, and providing, responsive to a determination that the response is a match, a next prompt, or provide a solution to the problem, the next prompt associated with expected responses to the next prompt.

Abstract: Generally discussed herein are devices, systems, and methods for detecting a conversation with a virtual agent is offtrack and responding appropriately. A method can include receiving a prompt, expected responses to the prompt, and a response of an interaction session with the virtual agent, the interaction session to solve a problem of a user, determining whether the response indicates the interaction session is in an offtrack state based on the prompt, expected responses, and response, in response to a determination that the interaction session is in the offtrack state, determining a taxonomy of the offtrack state, and providing, based on the determined taxonomy, a next prompt to the interaction session.

Abstract: Pre-saved concatenation cost data is compressed through speech segment grouping. Speech segments are assigned to a predefined number of groups based on their concatenation cost values with other speech segments. A representative segment is selected for each group. The concatenation cost between two segments in different groups may then be approximated by that between the representative segments of their respective groups, thereby reducing an amount of concatenation cost data to be pre-saved.

Abstract: Pre-saved concatenation cost data is compressed through speech segment grouping. Speech segments are assigned to a predefined number of groups based on their concatenation cost values with other speech segments. A representative segment is selected for each group. The concatenation cost between two segments in different groups may then be approximated by that between the representative segments of their respective groups, thereby reducing an amount of concatenation cost data to be pre-saved.