Method and System for Automatically Detecting Morphemes in a Task Classification System Using Lattices

• US 20130185059A1
• Filed: 03/04/2013
• Published: 07/18/2013
• Est. Priority Date: 11/05/1999
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Riccardi, Giuseppe
• Granted Patent: US 8,612,212 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/07 to the speaker
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/24 Speech recognition using non-acoustical features
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units
• CPC Class Codes: G10L 25/27 characterised by the analysis technique

Abstract

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.

Claims

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, result in the processor performing 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 medium having instructions stored which, when executed by a computing device, result in the computing device performing 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 medium of claim 18, wherein the detecting of the morphemes comprises using a confidence function.

20. The computer-readable storage medium of claim 18, wherein the new phonotactic model is used when recognizing phonemes for a future input from the user.