A method and system are disclosed herein for accepting multimodal inputs and deriving synchronized and processed information. A reusable multimodal application is provided on the mobile device. A user transmits a multimodal command to the multimodal platform via the mobile network. The one or more modes of communication that are inputted are transmitted to the multimodal platform(s) via the mobile network(s) and thereafter synchronized and processed at the multimodal platform. The synchronized and processed information is transmitted to the multimodal application. If required, the user verifies and appropriately modifies the synchronized and processed information. The verified and modified information are transferred from the multimodal application to the visual application. The final result(s) are derived by inputting the verified and modified results into the visual application.

A method for establishing a second communication according to a second modality on based on a first communication established according to a first modality between a communication terminal and an interactive server, the server reacting, according to a predefined logic, to commands received from the terminal, the logic being predefined by states and by conditions of transitions between the states. The method includes the server: obtaining a command for establishing a second communication according to a second modality; storing a context representative of interactions taken place between the terminal and the server in the course of the first communication in association with a public identity, the context including a state occupied by the server in the course of the first communication; establishing the second communication according to the second modality toward a recipient terminal designated by the stored public identity; and configuring the second communication based on the stored context.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a dialog system using user feedback. According to one implementation, a method includes receiving, by a dialog engine and from a computing device, a voice input, determining, by the dialog engine, that the received voice input is classified as feedback to an answer of a question; identifying, by the dialog engine, a predetermined feedback scare associated with the feedback; and adjusting a confidence score associated with the question and the answer based on the predetermined feedback score.

A method for phoneme identification. The method includes receiving an audio signal from a speaker, performing initial processing comprising filtering the audio signal to remove audio features, the initial processing resulting in a modified audio signal, transmitting the modified audio signal to a phoneme identification method and a phoneme replacement method to further process the modified audio signal, and transmitting the modified audio signal to a speaker. Also, a system for identifying and processing audio signals. The system includes at least one speaker, at least one microphone, and at least one processor, wherein the processor processes audio signals received using a method for phoneme replacement.

Disclosed is a work process supporting system based on interactive voice and text communication, and more particularly a work process supporting system based on interactive voice and text communication, in which at least one of a voice and a text is selectively applied according to congenital/acquired conditions of an information or service requester, so that a work process for providing information or service can be carried out, thereby freeing from constraints in input/output means for performing the work process for providing the information or the service and carrying out the work process while keeping continuity, reliability and accuracy.

A software app for a smartphone recognizes input from the user (such as the initial digits of a phone number) that identifies the organization to be called, and accesses remotely stored representations of information about the organization along with the IVR phone tree information for that organization. The app then presents a graphical representation of all or part of the retrieved information on a display. The user can then respond to the graphical representation by providing selective inputs that cause the synthesis all or part of the dialstring needed to navigate the phone tree to the desired destination. Once a dialing option has been synthesized, the user may provide additional input that the system interprets as an instruction to open a phone call and send a text message using the synthesized number.

Various embodiments of the present disclosure relate generally to providing services to users via communication channels. More specifically, various embodiments of the present disclosure relate to systems and methods for modifying, updating, and/or changing communication channel interactions based on the tracking or listening for events within other communication channels.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a dialog system using user feedback. According to one implementation, a method includes receiving, by a dialog engine and from a computing device, a voice input; determining, by the dialog engine, that the received voice input is classified as feedback to an answer of a question; identifying, by the dialog engine, a predetermined feedback score associated with the feedback; and adjusting a confidence score associated with the question and the answer based on the predetermined feedback score.

An example electronic apparatus for providing voice recognition control includes a display; and a processor, wherein the processor may be configured to obtain a content including at least one object; distinguish the at least one object within the content; display an instruction text in correspondence with a non-text object among the at least one object; and select the non-text object corresponding to the instruction text if a voice command corresponding to the instruction text is inputted.

A telephone subnet crawler is used to access automated telephone response systems and index the information, contents and structure contained therein. A database of the information, contents and structure of a plurality of automated telephone response systems is created by the telephone subnet crawler. A user interface provides a waiting party with direct access to the information, contents and structure of the automated telephone response systems contained in the database. Where an automated telephone response system requires user input, the user interface calls the automated telephone response system and navigates to the node requiring user input, provides the user input and displays the results to the user. Where an automated telephone response system connects to an operator, the user interface calls the automated telephone response system, navigates to the node for an operator, and when an operator is detected, calls the user at a user provided callback number.