Method and system for improving the fidelity of a dialog system
AssigneeHewlett-Packard Development Company, L.P.
InventorsSumit Roy, Michael Harville, Michele Covell
Life of this patent
Estimating the term…
Abstract
Embodiments of the present invention recite a method and system for improving the fidelity of a dialog system. In one embodiment, a first input generated by a user of a first system operating in a first modality is accessed. In embodiments of the present invention, the first system also generates a first output corresponding to the first input. An second input from a second user, who is engaged in a conversation with the first user, is accessed by a second system. The second input is then utilized to modify the first output of the first system.
Claims33
A method for improving the fidelity of a dialog system, said method comprising:
- accessing a first input generated by a user of a first system operating in a first modality and wherein said first system generates a first output corresponding to said first input;
- accessing a second input generated by a user of a second system operating in a second modality and wherein said user of said first system and said user of said second system are engaged in a conversation;
- and
- utilizing said second input to modify said first output of said first system.
A computer usable medium having computer readable program code embodied therein for causing a computer system to perform a method for improving the fidelity of a dialog system, said method comprising:
- accessing a first input generated by a user of a first system operating in a first modality and wherein said first system generates a first output corresponding to said first input;
- accessing a second input generated by a user of a second system operating in a second modality and wherein said user of said first system and said user of said second system are engaged in a conversation;
- and
- utilizing said second input to modify said first output of said first system.
A system for facilitating a conversation comprising:
- a first system in a first modality for accessing a first input and generating a first output corresponding to said first input;
- a second system in a second modality communicatively coupled with said first system and for accessing a second input and generating a second output corresponding to said second input;
- and
- a modification component communicatively coupled with said second system and for modifying said first output of said first system based upon said second input to second system.
A modification component for improving the fidelity of text-to-speech and automatic speech recognition systems, said system comprising:
- a first input accessor for accessing a first input for a first system in first modality, and wherein said first system generates a first output corresponding to said first input;
- a second input accessor for accessing a second input for a second system in a second modality;
- and
- a determining component for determining that said second input corresponds with said first input and for causing said first system to modify said first output based upon said second input.
Dependencies are inferred from the claim text.