Method, Apparatus and Computer Program Product for Providing Adaptive Language Model Scaling

• US 20080004877A1
• Filed: 06/30/2006
• Published: 01/03/2008
• Est. Priority Date: 06/30/2006
• Status: Active Grant

• Current Assignee: Nokia Corporation
• Original Assignee: Nokia Corporation
• Inventors: Tian, Jilei
• Granted Patent: US 7,716,049 B2
• Time in Patent Office: Days
• US Class Current: 704/251
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams

Abstract

An apparatus for providing adaptive language model scaling includes an adaptive scaling element and an interface element. The adaptive scaling element is configured to receive input speech comprising a sequence of spoken words and to determine a plurality of candidate sequences of text words in which each of the candidate sequences has a corresponding sentence score representing a probability that a candidate sequence matches the sequence of spoken words. Each corresponding sentence score is calculated using an adaptive scaling factor. The interface element is configured to receive a user input selecting one of the candidate sequences. The adaptive scaling element is further configured to estimate an objective function based on the user input and to modify the adaptive scaling factor based on the estimated objective function.

Claims

1. A method comprising:

receiving input speech comprising a sequence of spoken words;

determining a plurality of candidate sequences of text words in which each of the candidate sequences has a corresponding sentence score representing a probability that a candidate sequence matches the sequence of spoken words, each corresponding sentence score being calculated using an adaptive scaling factor;

receiving a user input selecting one of the candidate sequences;

estimating an objective function based on the user input; and

modifying the adaptive scaling factor based on the estimated objective function.

2. A method according to claim 1, further comprising generating a word lattice including a series of candidate words corresponding to each of the spoken words in the sequence of spoken words, each of the candidate words having a corresponding word score.

3. A method according to claim 2, further comprising determining the word score of each of the candidate words by summing an acoustic score and a language score for each word, wherein at least one of the acoustic score or the language score is weighted according to the adaptive scaling factor.

4. A method according to claim 3, wherein determining the plurality of candidate sequences of text words comprises determining each of the candidate sequences responsive to a summation of selected word candidates.

5. A method according to claim 1, further comprising calculating the sentence score by summing an acoustic score and a language score for each candidate sequence, and wherein at least one of the acoustic score or the language score is weighted according to the adaptive scaling factor.

6. A method according to claim 1, wherein estimating the objective function is performed based on the user input and a collection of recently used candidate sequences.

7. A method according to claim 6, further comprising applying a forgetting factor to define the collection of recently used candidate sequences.

8. A method according to claim 7, wherein applying the forgetting factor comprises one of:

defining the collection based on age of recently used sentences;

or

defining the collection to be a predetermined number of recently used sentences.

9. A method according to claim 1, wherein modifying the adaptive scaling factor comprises adjusting the adaptive scaling factor by an amount determined by estimating the objective function.

10. A method according to claim 9, wherein adjusting the adaptive scaling factor improves the sentence score of the user selected one of the candidate sequences.

11. A computer program product comprising at least one computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

a first executable portion for receiving input speech comprising a sequence of spoken words;

a second executable portion for determining a plurality of candidate sequences of text words in which each of the candidate sequences has a corresponding sentence score representing a probability that a candidate sequence matches the sequence of spoken words, each corresponding sentence score being calculated using an adaptive scaling factor;

a third executable portion for receiving a user input selecting one of the candidate sequences;

a fourth executable portion for estimating an objective function based on the user input; and

a fifth executable portion for modifying the adaptive scaling factor based on the estimated objective function.

12. A computer program product according to claim 11, further comprising a sixth executable portion for generating a word lattice including a series of candidate words corresponding to each of the spoken words in the sequence of spoken words, each of the candidate words having a corresponding word score.

13. A computer program product according to claim 12, further comprising a seventh executable portion for determining the word score of each of the candidate words by summing an acoustic score and a language score for each word, wherein at least one of the acoustic score or the language score is weighted according to the adaptive scaling factor.

14. A computer program product according to claim 13, wherein the second executable portion includes instructions for determining each of the candidate sequences responsive to a summation of selected word candidates.

15. A computer program product according to claim 11, further comprising a sixth executable portion for calculating the sentence score by summing an acoustic score and a language score for each candidate sequence, and wherein at least one of the acoustic score or the language score is weighted according to the adaptive scaling factor.

16. A computer program product according to claim 11, wherein the fourth executable portion is executed based on the user input and a collection of recently used candidate sequences.

17. A computer program product according to claim 16, further comprising a sixth executable portion for applying a forgetting factor to define the collection of recently used candidate sequences.

18. A computer program product according to claim 17, wherein the sixth executable portion includes instructions for one of:

defining the collection based on age of recently used sentences;

or

defining the collection to be a predetermined number of recently used sentences.

19. A computer program product according to claim 11, wherein the fifth executable portion includes instruction for adjusting the adaptive scaling factor by an amount determined by estimating the objective function.

20. A computer program product according to claim 19, wherein the fifth executable portion includes instruction for adjusting the adaptive scaling factor to improve the sentence score of the user selected one of the candidate sequences.

21. An apparatus comprising:

a adaptive scaling element configured to receive input speech comprising a sequence of spoken words and to determine a plurality of candidate sequences of text words in which each of the candidate sequences has a corresponding sentence score representing a probability that a candidate sequence matches the sequence of spoken words, each corresponding sentence score being calculated using an adaptive scaling factor; and

an interface element configured to receive a user input selecting one of the candidate sequences,

wherein the adaptive scaling element is further configured to estimate an objective function based on the user input and to modify the adaptive scaling factor based on the estimated objective function.

22. An apparatus according to claim 21, wherein the adaptive scaling element is configured to generate a word lattice including a series of candidate words corresponding to each of the spoken words in the sequence of spoken words, each of the candidate words having a corresponding word score.

23. An apparatus according to claim 22, wherein the adaptive scaling element is configured to determine the word score of each of the candidate words by summing an acoustic score and a language score for each word, wherein at least one of the acoustic score or the language score is weighted according to the adaptive scaling factor.

24. An apparatus according to claim 23, wherein the adaptive scaling element is configured to determine each of the candidate sequences responsive to a summation of selected word candidates.

25. An apparatus according to claim 21, wherein the adaptive scaling element is configured to calculate the sentence score by summing an acoustic score and a language score for each candidate sequence, and wherein at least one of the acoustic score or the language score is weighted according to the adaptive scaling factor.

26. An apparatus according to claim 21, wherein the adaptive scaling element is configured to estimate the objective function based on the user input and a collection of recently used candidate sequences.

27. An apparatus according to claim 26, wherein the adaptive scaling element is configured to apply a forgetting factor to define the collection of recently used candidate sequences.

28. An apparatus according to claim 27, wherein the adaptive scaling element is configured to perform one of:

defining the collection based on age of recently used sentences;

or

defining the collection to be a predetermined number of recently used sentences.

29. An apparatus according to claim 21, wherein the adaptive scaling element is configured to adjust the adaptive scaling factor by an amount determined by estimating the objective function.

30. An apparatus according to claim 29, wherein the adaptive scaling element is configured to adjust the adaptive scaling factor to improve the sentence score of the user selected one of the candidate sequences.

31. An apparatus according to claim 21, wherein the apparatus is embodied as a mobile terminal.

32. An apparatus comprising:

means for receiving input speech comprising a sequence of spoken words;

means for determining a plurality of candidate sequences of text words in which each of the candidate sequences has a corresponding sentence score representing a probability that a candidate sequence matches the sequence of spoken words, each corresponding sentence score being calculated using an adaptive scaling factor;

means for receiving a user input selecting one of the candidate sequences;

means for estimating an objective function based on the user input; and

means for modifying the adaptive scaling factor based on the estimated objective function.