Hierarchical language models

• US 20020123891A1
• Filed: 03/01/2001
• Published: 09/05/2002
• Est. Priority Date: 03/01/2001
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Epstein, Mark E.
• Granted Patent: US 6,754,626 B2
• Time in Patent Office: Days
• US Class Current: 704/235
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams

Abstract

The invention disclosed herein concerns a method of converting speech to text using a hierarchy of contextual models. The hierarchy of contextual models can be statistically smoothed into a language model. The method can include processing text with a plurality of contextual models. Each one of the plurality of contextual models can correspond to a node in a hierarchy of the plurality of contextual models. Also included can be identifying at least one of the contextual models relating to the text and processing subsequent user spoken utterances with the identified at least one contextual model.

Claims

1. A method of converting speech to text using a hierarchy of contextual models wherein said hierarchy of contextual models is statistically smoothed into a language model, said method comprising:

(a) processing text with a plurality of contextual models, wherein each one of said plurality of contextual models corresponds to a node in a hierarchy of said plurality of contextual models;

(b) identifying at least one of said contextual models relating to said text; and

(c) processing subsequent user spoken utterances with said identified at least one contextual model.

2. The method of claim 1, wherein said step (a) is performed serially.

3. The method of claim 1, wherein said step (a) is performed in parallel.

4. The method of claim 1, wherein at least one of said plurality of contextual models corresponds to a document or a portion of a document.

5. The method of claim 1, wherein at least one of said plurality of contextual models corresponds to a section of a document.

6. The method of claim 1, wherein at least one of said plurality of contextual models corresponds to at least one user response received in a particular dialog state in a dialog based system.

7. The method of claim 1, wherein at least one of said plurality of contextual models corresponds to at least one user response received at a particular location within a particular transaction within a dialog based system.

8. The method of claim 1, wherein at least one of said plurality of contextual models corresponds to the syntax of a prompt in a dialog based system.

9. The method of claim 1, wherein at least one of said plurality of contextual models corresponds to a particular and known dialog based system prompt.

10. The method of claim 1, wherein at least one of said plurality of contextual models corresponds to a received electronic mail message.

11. A method of creating a hierarchy of contextual models, said method comprising:

(a) measuring the distance between each of a plurality of contextual models using a distance metric, wherein at least one of said plurality of contextual models corresponds to a portion of a document or a user response within a dialog based system;

(b) identifying two of said plurality of contextual models, said identified contextual models being closer in distance than other ones of said plurality of contextual models;

(c) merging said identified contextual models into a parent contextual model;

(d) repeating said steps (a), (b), and (c) until a hierarchy of said plurality of contextual models is created, said hierarchy having a root node; and

(e) statistically smoothing said hierarchy of said plurality of contextual models resulting in a language model.

12. The method of claim 11, said merging step (c) further comprising:

interpolating between said identified contextual models, said interpolation resulting in a combination of said identified contextual models.

13. The method of claim 11, said merging step (c) further comprising:

building a parent contextual model using data corresponding to said identified contextual models.

14. The method of claim 11, wherein at least one of said plurality of contextual models corresponds to a section of a document.

16. The machine readable storage of claim 15, wherein said step (a) is performed serially.

17. The machine readable storage of claim 15, wherein said step (a) is performed in parallel.

18. The machine readable storage of claim 15, wherein at least one of said plurality of contextual models corresponds to a document or a portion of a document.

19. The machine readable storage of claim 15, wherein at least one of said plurality of contextual models corresponds to a section of a document.

20. The machine readable storage of claim 15, wherein at least one of said plurality of contextual models corresponds to at least one user response received in a particular dialog state in a dialog based system.

21. The machine readable storage of claim 15, wherein at least one of said plurality of contextual models corresponds to at least one user response received at a particular location within a particular transaction within a dialog based system.

22. The machine readable storage of claim 15, wherein at least one of said plurality of contextual models corresponds to the syntax of prompt in a dialog based system.

23. The machine readable storage of claim 15, wherein at least one of said plurality of contextual models corresponds to a particular and known dialog based system prompt.

24. The machine readable storage of claim 15, wherein at least one of said plurality of contextual models corresponds to a received electronic mail message.

26. The machine readable storage of claim 25, said merging step (c) further comprising:

interpolating between said identified contextual models, said interpolation resulting in a combination of said identified contextual models.

27. The machine readable storage of claim 25, said merging step (c) further comprising:

building a parent contextual model using data corresponding to said identified contextual models.

28. The machine readable storage of claim 25, wherein at least one of said plurality of contextual models corresponds to a section of a document.

15. A machine readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

(a) processing text with a plurality of contextual models, wherein each one of said plurality of contextual models corresponds to a node in a hierarchy of said plurality of contextual models;

(b) identifying at least one of said contextual models relating to said text; and

(c) processing subsequent user spoken utterances with said identified at least one contextual model.

25. A machine readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform the steps of:

(a) measuring the distance between each of a plurality of contextual models using a distance metric, wherein at least one of said plurality of contextual models corresponds to a portion of a document or a user response within a dialog based system;

(b) identifying two of said plurality of contextual models, said identified contextual models being closer in distance than other ones of said plurality of contextual models;

(c) merging said identified contextual models into a parent contextual model;

(d) repeating said steps (a), (b), and (c) until a hierarchy of said plurality of contextual models is created, said hierarchy having a root node; and

(e) statistically smoothing said hierarchy of said plurality of contextual models resulting in a language model.