Method and system for automatically detecting morphemes in a task classification system using lattices
View Patent ↗The invention concerns a method and corresponding system for building a phonotactic model for domain independent speech recognition. The method may include recognizing phones from a user's input communication using a current phonotactic model, detecting morphemes (acoustic and/or non-acoustic) from the recognized phones, and outputting the detected morphemes for processing. The method also updates the phonotactic model with the detected morphemes and stores the new model in a database for use by the system during the next user interaction. The method may also include making task-type classification decisions based on the detected morphemes from the user's input communication.
1. A method comprising:
recognizing phonemes from a user input using a current phonotactic model stored in a database, to yield recognized phonemes;
detecting morphemes from the recognized phonemes;
creating, via a processor, a new phonotactic model by transforming, using the morphemes, a prior probability distribution associated with a first domain to a prior probability distribution associated with a second domain; and
replacing the current phonotactic model with the new phonotactic model in the database.
2. The method of claim 1 , wherein the morphemes comprise one of verbal speech and non-verbal speech.
3. The method of claim 2 , wherein the non-verbal speech comprises using one of a gesture, a body movement, a head movement, a non-response, text, a keyboard entry, a keypad entry, a mouse click, a dual-tone machine frequency code, a pointer, a stylus, a graphical user interface, and a touchscreen entry.
4. The method of claim 2 , wherein the user input further comprises an environment of the user.
5. The method of claim 1 , wherein the morphemes are expressed in multimodal form.
6. The method of claim 1 , wherein the morphemes in the user input are derived from an action of the user.
7. The method of claim 6 , wherein the action of the user comprises a focus of attention of the user.
8. The method of claim 1 , operating in conjunction with one of a telephone network, Internet, an intranet, a cable television network, a local area network, and a wireless communication network.
9. The method of claim 1 , wherein the method is used for customer care purposes.
10. The method of claim 1 , wherein the morphemes are detected using a measure of commonality within a language of the morphemes.
11. The method of claim 1 , wherein the detecting of the morphemes comprises using a confidence function.
12. The method of claim 1 , wherein the new phonotactic model is used when recognizing phonemes for a future input from the user.
13. A system comprising:
a processor; and
a computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising:
recognizing phonemes from a user input using a current phonotactic model stored in a database, to yield recognized phonemes;
detecting morphemes from the recognized phonemes;
creating, via a processor, a new phonotactic model by transforming, using the morphemes, a prior probability distribution associated with a first domain to a prior probability distribution associated with a second domain; and
replacing the current phonotactic model with the new phonotactic model in the database.
14. The system of claim 13 , wherein the morphemes comprise one of verbal speech and non-verbal speech.
15. The system of claim 14 , wherein the non-verbal speech comprises using one of a gesture, a body movement, a head movement, a non-response, text, a keyboard entry, a keypad entry, a mouse click, a dual-tone machine frequency code, a pointer, a stylus, a graphical user interface, and a touchscreen entry.
16. The system of claim 14 , wherein the user input further comprises an environment of the user.
17. The system of claim 13 , wherein the morphemes are expressed in multimodal form.
18. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising:
recognizing phonemes from a user input using a current phonotactic model stored in a database, to yield recognized phonemes;
detecting morphemes from the recognized phonemes;
creating, via a processor, a new phonotactic model by transforming, using the morphemes, a prior probability distribution associated with a first domain to a prior probability distribution associated with a second domain; and
replacing the current phonotactic model with the new phonotactic model in the database.
19. The computer-readable storage device of claim 18 , wherein the detecting of the morphemes comprises using a confidence function.
20. The computer-readable storage device of claim 18 , wherein the new phonotactic model is used when recognizing phonemes for a future input from the user.