Abstract: The operation of an application on a first device may be guided by a user operating a second device. The application on the first device may present a character on a display of the first device and obtain an audio signal of speech of a user of the first device. Audio data may be transmitted to the second device and corresponding audio may be played from speakers of the second device. The second device may present suggestions of phrases to be spoken by the character displayed on the first device. A user of the second device may select a phrase to be spoken by the character. Phrase data may be transmitted to the first device, and the first device may generate audio of the character speaking the phrase using a text-to-speech voice associated with the character.

Abstract: A service may be provided that allows interacting users to interact with characters presented by devices of the interacting users. The operation of the character presented to an interacting user may be customized for that interacting user. For example, a first controlling user may specify first information for configuring or controlling the operation of the character when the character is interacting with a first interacting user, and a second controlling user may specify second information for configuring or controlling the operation of the character when the character is interacting with a second interacting user. The information provided by a controlling user may be used to select a segment to be used for a session between an interacting user and the character.

Abstract: Assistance may be provided to a first user of a first device by monitoring sensors of the first device and providing assistance via a character presented by the device. Sensor data, such as audio, video, or biometric data, may be transmitted to a server, and a server may process the sensor data to determine a state of the first user. The server may determine to request assistance based on the state of the first user. The server may then send a request to a second device of a second user to guide the character presented by the first device. The second user may then provide assistance to the first user by guiding the character presented by the first device.

Abstract: A service may be provided that allows interacting users to interact with characters presented by devices of the interacting users. The operation of the character presented to an interacting user may be customized for that interacting user. For example, a first controlling user may specify first information for configuring or controlling the operation of the character when the character is interacting with a first interacting user, and a second controlling user may specify second information for configuring or controlling the operation of the character when the character is interacting with a second interacting user. The information provided by a controlling user may be used to select a segment to be used for a session between an interacting user and the character.

Abstract: A first user of a first device may interact with a character presented on the first device where the character presented on the first device is guided by a second user of a second device. To begin a communications session, the first user may request to communicate with the character. A server may process the request to speak with the character and identify the second user from a plurality of guiding users, where the second user is identified by comparing profile information of the first user with profile information of the second user. The server may then send a request to the second device of the second user to guide the character presented by the first device. The first user may then communicate with the character with the guidance of the second user.

Abstract: A user of a device may interact with a character presented by the device. A session between the user and the character may be started by a user, may be triggered by an event, or may be started in other ways. The user of the of the device may be associated with one or more trigger events. Information about the trigger events may be obtained and processed to determine when a trigger event has occurred. When a trigger event has occurred, a session may be started on the device with the character. A segment may be selected to be presented during the session, and an interaction corresponding to the segment may be presented by the character to the user. For example, the character may speak a phrase using a text-to-speech voice.

Abstract: The operation of an application on a first device may be guided by a user operating a second device. The application on the first device may present a character on a display of the first device and obtain an audio signal of speech of a user of the first device. Audio data may be transmitted to the second device and corresponding audio may be played from speakers of the second device. The second device may present suggestions of phrases to be spoken by the character displayed on the first device. A user of the second device may select a phrase to be spoken by the character. Phrase data may be transmitted to the first device, and the first device may generate audio of the character speaking the phrase using a text-to-speech voice associated with the character.

Abstract: The operation of an application on a first device may be guided by a user operating a second device. The application on the first device may present a character on a display of the first device and obtain an audio signal of speech of a user of the first device. Audio data may be transmitted to the second device and corresponding audio may be played from speakers of the second device. The second device may present suggestions of phrases to be spoken by the character displayed on the first device. A user of the second device may select a phrase to be spoken by the character. Phrase data may be transmitted to the first device, and the first device may generate audio of the character speaking the phrase using a text-to-speech voice associated with the character.

Abstract: The operation of an application on a first device may be guided by a user operating a second device. The application on the first device may present a character on a display of the first device and obtain an audio signal of speech of a user of the first device. Audio data may be transmitted to the second device and corresponding audio may be played from speakers of the second device. The second device may present suggestions of phrases to be spoken by the character displayed on the first device. A user of the second device may select a phrase to be spoken by the character. Phrase data may be transmitted to the first device, and the first device may generate audio of the character speaking the phrase using a text-to-speech voice associated with the character.

Abstract: A call from a caller to an interactive voice response (IVR) system may be serviced based on behavior by the caller in one or more prior calls to the IVR system. The call may be serviced by predicting information to be used in servicing the call. Predicting such information may include analyzing data reflecting behavior by the caller in one or more prior calls to the IVR system.

Abstract: Call service centers typically require a user to confirm its identity by manually entering identification. An embodiment of the present invention uses a client device's identification to identify a user securely without requiring a user to enter identification manually. The client device's automatic numbering identification (ANI) number is an example of identification of the user, and the client device's media access control address is an example of information used, as an encryption key, to verify that the ANI number is not spoofed. In one embodiment, the client device provides the ANI number to a data server prior to a call, and the data server provides information to enable enhancement of the call either by sending the information to the call center directly or via the client device. Benefits of embodiments of the present invention include a reduced load on call service centers, reduced call time, and increased user satisfaction.

Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.

Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.

Abstract: Call service centers typically require a user to confirm its identity by manually entering identification. An embodiment of the present invention uses a client device's identification to identify a user securely without requiring a user to enter identification manually. The client device's automatic numbering identification (ANI) number is an example of identification of the user, and the client device's media access control address is an example of information used, as an encryption key, to verify that the ANI number is not spoofed. In one embodiment, the client device provides the ANI number to a data server prior to a call, and the data server provides information to enable enhancement of the call either by sending the information to the call center directly or via the client device. Benefits of embodiments of the present invention include a reduced load on call service centers, reduced call time, and increased user satisfaction.

Abstract: A call from a caller to an interactive voice response (IVR) system may be serviced based on behavior by the caller in one or more prior calls to the IVR system. The call may be serviced by predicting information to be used in servicing the call. Predicting such information may include analyzing data reflecting behavior by the caller in one or more prior calls to the IVR system.

Abstract: A call from a caller to an interactive voice response (IVR) system may be serviced based on behavior by the caller in one or more prior calls to the IVR system. The call may be serviced by predicting information to be used in servicing the call. Predicting such information may include analyzing data reflecting behavior by the caller in one or more prior calls to the IVR system.

Abstract: A system and method enable a designer to design an application using a design tool, deploy the application for execution, and subsequently view statistics related to the execution within the design tool. The designer uses the design tool to create an application flow for the application, and the design tool then generates software code for such application. In generating software code, the design tool inserts markers in the application code that demarks the boundaries between nodes in the application flow. When the application is executed, a log is created in accordance with the markers such that data is logged for nodes traversed during the execution of the application. Using the logged data, statistics are calculated for one or more of the nodes. These statistics are provided to the design tool and, in the preferred embodiment, displayed in conjunction with the application flow in the user interface of the design tool.

Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.

Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.

Abstract: Techniques for generating synthetic speech with contrastive stress. In one aspect, a speech-enabled application generates a text input including a text transcription of a desired speech output, and inputs the text input to a speech synthesis system. The synthesis system generates an audio speech output corresponding to at least a portion of the text input, with at least one portion carrying contrastive stress, and provides the audio speech output for the speech-enabled application. In another aspect, a speech-enabled application inputs a plurality of text strings, each corresponding to a portion of a desired speech output, to a software module for rendering contrastive stress. The software module identifies a plurality of audio recordings that render at least one portion of at least one of the text strings as speech carrying contrastive stress. The speech-enabled application generates an audio speech output corresponding to the desired speech output using the audio recordings.