Nametag confusability determination

1. A method of managing nametags, comprising the steps of:

(a) receiving a command from a user to store a nametag;

(b) prompting the user to input a number to be stored in association with the nametag;

(c) receiving an input for the number from the user;

(d) prompting the user to input the nametag to be stored in association with the number;

(e) receiving an input for the nametag from the user;

(f) processing the nametag input from step (e), by decoding the nametag input using at least one statistical language model trained on multiple semantic domains including a semantic nametag domain and a semantic number domain to provide a recognition result for the nametag input;

(g) determining confusability of the nametag input by using at least one semantic classifier trained on the multiple semantic domains to classify the recognition result with a confidence score for each of the domains as an indication of the likelihood that the nametag input is within a particular one of the domains, and by comparing the confidence scores for the multiple semantic domains to at least one confusability threshold; and

(h) prompting the user to input a different nametag to be stored in association with the number, if the confidence score associated with the semantic number domain exceeds the confusability threshold.

2. The method of claim 1 , further comprising the step of (i) retraining the SLM and semantic classifier using the nametag input if the nametag input was not determined to be confusable.

3. The method of claim 1 , wherein the at least one confusability threshold is the same for the semantic nametag and number domains.

4. The method of claim 1 , wherein the at least one confusability threshold includes a nametag confusability threshold and a number confusability threshold, wherein the confusability thresholds are all different from one another.

5. A computer program product including instructions on a non-transitory computer readable medium and executable by a computer processor of a system to cause the system to implement steps recited in claim 1 .

6. A method of managing nametags, comprising the steps of:

(a) receiving a command from a user to store a nametag;

(b) prompting the user to input a number to be stored in association with the nametag;

(c) receiving an input for the number from the user;

(d) prompting the user to input the nametag to be stored in association with the number;

(e) receiving an input for the nametag from the user, in the form of a text entry;

(f) processing the nametag input from step (e) including converting the text entry to a sequence of phonemes, and using at least one statistical language model trained on multiple independent domains to provide a recognition result for the nametag input, wherein the domains include a nametag domain and a multiple-digit telephone number domain that is smaller than the different combinations of a ten digit number;

(g) calculating confusability based on a comparison of the text entry sequence of phonemes to phonemes of entries in the multiple independent domains by using at least one semantic classifier trained on the multiple independent domains to classify the recognition result with a confidence score for each of the domains as an indication of the likelihood that the nametag input is within a particular one of the domains, and by comparing the confidence score for each of the domains to at least one confusability threshold; and

(h) prompting the user to input a different nametag to be stored in association with the number, if the confidence score exceeds the at least one confusability threshold.

7. The method of claim 6 , wherein the phoneme-based confusability score is minimum if the sequence of phonemes converted from the text entry does not correspond to phonemes of any stored entry in any of the domains, and the phoneme-based confusability score is maximum if the sequence of phonemes converted from the text entry corresponds identically to a sequence of phonemes of any stored entry in any of the domains.

8. A system to manage nametags, comprising:

an interface, including a microphone, to receive a command from a user to store a nametag, prompt the user to enter a number to be stored in association with the nametag, receive a number input for the number from the user, prompt the user to enter the nametag to be stored in association with the number, and receive a nametag input for the nametag from the user via the microphone; and

a processor in communication with the interface and including:

a decoder to process the nametag input to provide a recognition result by decoding the nametag input using at least one statistical language model trained on multiple semantic domains including a semantic nametag domain and a semantic number domain;

at least one semantic classifier trained on the multiple semantic domains to classify the recognition result with a confidence score for each of the domains as an indication of the likelihood that the nametag input is within a particular one of the domains; and

a post-processor to receive the recognition result from the decoder and use the recognition result as input to determine confusability of the nametag input in the multiple domains by comparing the confidence score to at least one confusability threshold, and to prompt the user to input a different nametag to be stored in association with the number, if the confidence score exceeds the confusability threshold.

9. The system of claim 8 , wherein the nametag input is an utterance from the user and the decoder decodes the utterance using a statistical language model (SLM) and a semantic classifier trained on the nametag domain, the number domain, and the command domain, and the post-processor retrains the SLM and semantic classifier using the nametag input if the nametag input is not determined to be confusable.

10. The system of claim 9 , wherein the decoder produces an N-best list of hypotheses and associated confidence scores, and the post-processor calculates the confusability based on at least one of the confidence scores.

11. The system of claim 8 , wherein the nametag input is a text entry from the user and the decoder converts the text entry to a sequence of phonemes, and the post-processor calculates the confusability based on a comparison of the text entry sequence of phonemes to phonemes of entries in at least one of the domains.