PATTERN PROCESSING SYSTEM SPECIFIC TO A USER GROUP

• US 20150179164A1
• Filed: 03/03/2015
• Published: 06/25/2015
• Est. Priority Date: 06/06/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Beyerlein, Peter
• Granted Patent: US 9,424,838 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/07 to the speaker

Abstract

Methods and apparatus for identifying a user group in connection with user group-based speech recognition. An exemplary method comprises receiving, from a user, a user group identifier that identifies a user group to which the user was previously assigned based on training data. The user group comprises a plurality of individuals including the user. The method further comprises using the user group identifier, identifying a pattern processing data set corresponding to the user group, and receiving speech input from the user to be recognized using the pattern processing data set.

Claims

1. A method for identifying a user group in connection with speech recognition, the method comprising:

receiving, by at least one computer, a user group identifier that identifies a user group to which a plurality of users including a first user were assigned prior to the at least one computer receiving the user group identifier;

wherein the assignment of the first user to the user group was based at least in part on one or more speech utterances of the first user, and

wherein the user group identifier uniquely identifies a pattern processing data set shared by the plurality of users assigned to the user group; and

receiving, by the at least one computer, speech input from the first user to be recognized using the pattern processing data set.

2. The method of claim 1, further comprising acts of:

receiving training pattern speech input from the user; and

assigning the user group identifier to the user based on the training pattern speech input.

3. The method of claim 1, wherein the user group identifier comprises a numeric code.

4. The method of claim 1, wherein the user group identifier comprises a symbolic name.

5. The method of claim 1, further comprising accessing, via a at least one network, the pattern processing data set.

6. The method of claim 1, further comprising performing recognition of the speech input using the pattern processing data set.

7. The method of claim 1, wherein the pattern processing data set includes at least one acoustic model and/or at least one language model.

8-20. -20. (canceled)

21. A method comprising:

transmitting, to at least one server, a user group identifier that identifies a user group to which a plurality of users including a first user were previously assigned prior to transmitting the user group identifier,

wherein the assignment of the first user to the user group was based at least in part on one or more speech utterances of the first user, and

wherein the user group identifier uniquely identifies a pattern processing data set shared by the plurality of users assigned to the user group; and

providing speech input from the first user to be recognized using the identified pattern processing data set.

22. The method of claim 21, further comprising receiving recognized text resulting from speech recognition of the speech input using the pattern processing data set.

23. The method of claim 21, further comprising receiving, by a user device, the pattern processing data set.

24. The method of claim 23, further comprising performing, by the user device, speech recognition based at least in part on the pattern processing data set and the speech input.