Nuance Communications, Inc.

Henri Bouvier

David Andrew Mauro

Elizabeth Ann Dykstra-Erickson

Aimee Piercy

Susan Dawnstarr Daniel

Stephen Douglas Peters

Paweena Attayadmawittaya

Andrew Jonathan Watson

Robert Douglas Sharp

Simona Gandrabur

A method of providing a task assistant to provide an interface to an application is described. The method comprises receiving input from a user through multimodal input including a plurality of speech input, typing input, and touch input, interpreting the input, and providing a formatted query to the application, receiving data from the application in response to the query, and providing a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output.

Task assistant

A method of providing a task assistant is described. The task assistant is designed to receive input from a user through multimodal input including a plurality of speech input, typing input, and touch input, determine the meaning of the input, and determining whether there is a context based on prior interactions with the user. The method further to generate an interpreted input based on a combination of the input and the context, and providing a formatted query to an application. The method further to receive data from the application in response to the formatted query, and provide a response to the user through multimodal output including a plurality of: speech output, text output, non-speech audio output, haptic output, and visual non-text output. The method further to update the context based on the interpreted input.

Task assistant utilizing context for improved interaction

A method of speech-enabling a human-to-machine interface comprises uniquely identifying a plurality of input fields and corresponding input field identifications (IDs) associated with a human-to-machine interface. The method further comprises mapping the input field IDs to grammar slot names to produce a speech-to-field mapping. The grammar slot names may be associated with speech-to-text rendering of speech expected to be received by a speech-to-text renderer configured to output representations of the speech having correspondence with the grammar slot names. The method also comprises enabling a flow of representations of speech to the input fields via the speech-to-field mapping. The input fields may include interactive elements displayed on a screen view including at least one of radio buttons, text fields, buttons, and drop down menus. The human-to-machine interface may include at least one of a webpage, interactive software program, computerized input form, graphical user interface, visual display, or audio interface.

Methods and systems for speech-enabling a human-to-machine interface

Generally, human-to-machine interfaces are configured to accept speech input from a user. However, such interfaces, e.g., web browsers, must be configured to enable acceptance of speech input from the user. Some interfaces, such as mobile browsers, have less configuration adaptability and are not able to be configured to accept speech input from a user. Embodiments of the present invention speech-enable human-to-machine interfaces by loading content of the human-to-machine interface and adding logic configured to enable speech interaction with the content to the interface. The embodiment then activates speech interaction with the content via the logic for the user. Thus, embodiments of the present invention enable speech interaction with interfaces that are not configured to be adapted to allow speech interaction and are able to enable the speech interaction in a seamless manner.

Growing community of inventors

Montreal, Canada

Henri Bouvier