Eliminating interference of noisy modality in a multimodal application
Aspects of the present invention provide for ranking various input modalities relative to each other and processing recognition results received through these input modalities based in part on the ranking.
1. A method for processing inputs from a user into a computer, the method comprising:
ranking input modalities;
receiving responses from the user pursuant to a plurality of modalities including receiving a confidence measure for each response; and
processing, via a processing unit, the responses based on the rankings using a weighting factor for each input modality in combination with the associated confidence measure to select a user response to be used.
2. The method of claim 1 wherein processing the responses based on the rankings comprises deactivating lower ranked responses upon indications that a higher ranked input modality is being used by the user.
3. The method of claim 1 wherein processing the responses based on the rankings comprises selecting the response from the highest ranked input modality that has obtained a result.
4. The method of claim 1 wherein the input modalities comprise at least two input modalities from the group: voice recognition, DTMF recognition, computer vision recognition, handwriting recognition, keyboard input and pointing device input.
5. A computer-readable storage medium having instructions that would cause a processor to process inputs from a user into a computer, the instructions comprising:
i. receiving responses from the user pursuant to a plurality of modalities;
ii. receiving a confidence measure for each response; and
iii. processing the responses using a weighting factor for each input modality in combination with the associated confidence to select a user response to be used.
6. The computer readable storage medium of claim 5 wherein processing the responses based on the rankings comprises deactivating lower ranked responses upon indications that a higher ranked input modality is being used by the user.
7. The computer readable storage medium of claim 5 wherein processing the responses based on the rankings comprises selecting the response from the highest ranked input modality that has obtained a result.
8. The computer readable storage medium of claim 5 wherein the input modalities comprise at least two input modalities from the group: voice recognition, DTMF recognition, computer vision recognition, handwriting recognition, keyboard input and pointing device input.