System and method for processing speech recognition results

• US 7,219,058 B1
• Filed: 10/01/2001
• Issued: 05/15/2007
• Est. Priority Date: 10/13/2000
• Status: Expired due to Term

• Current Assignee: Interactions, LLC
• Original Assignee: AT&T Corporation (AT&T, Inc.)
• Inventors: Rose, Richard C., Pathasarathy, Sarangarajan, Rosenberg, Aaron Edward, Narayanan, Shrikanth Sambasivan
• Primary Examiner(s): Hudspeth, David
• Assistant Examiner(s): Jackson, Jakieda R.
• Application Number:
  US09/966,081
• Time in Patent Office: 2,052 Days
• Field of Search: 704/238, 704/256, 704/257, 704/231, 704/255, 704/2, 704/251, 704/220, 704/246, 704/240, 704/245, 704/239, 704/224, 704/260, 395/2.49, 385/2.41
• US Class Current: 704/238
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering

Abstract

An automatic speech recognition (ASR) system and method is provided for controlling the recognition of speech utterances generated by an end user operating a communications device. The ASR system and method can be used with a mobile device that is used in a communications network. The ASR system can be used for ASR of speech utterances input into a mobile device, to perform compensating techniques using at least one characteristic and for updating an ASR speech recognizer associated with the ASR system by determined and using a background noise value and a distortion value that is based on the features of the mobile device. The ASR system can be used to augment a limited data input capability of a mobile device, for example, caused by limited input devices physically located on the mobile device.

Claims

1. A method of rescoring the results of automatic speech recognition, comprising:

generating a plurality of lattices for received speech utterances associated with filling in a plurality of user selected data fields in a user interface;

concatenating the plurality of lattices into a single concatenated lattice; and

applying at least one language model to the single concatenated lattice in order to determine relationships between the plurality of lattices.

2. The method of rescoring the results of automatic speech recognition according to claim 1, further comprising generating a confidence score after applying the at least one speech recognition model to determine whether the plurality of lattices are acceptable.

3. The method of rescoring the results of automatic speech recognition according to claim 2, wherein the confidence score is compared to a predetermined value in order to determine whether to perform the automatic speech recognition process again.

4. The method of rescoring the results of automatic speech recognition according to claim 3, wherein the automatic speech recognition process is performed again if the confidence score is less than the predetermined value.

5. The method of rescoring the results of automatic speech recognition according to claim 1, wherein the rescoring is performed after a speech recognition model has been compensated to reflect acoustic environmental data and transducer data.

6. The method of rescoring the results of automatic speech recognition according to claim 1, wherein the rescoring the automatic speech recognition is used in a mobile communications system.

7. The method of rescoring the results of automatic speech recognition according to claim 1, wherein the rescoring the automatic speech recognition is used in a satellite communications system.

8. A rescoring process used in the automatic speech recognition system, comprising:

a speech recognizer that generates a plurality of lattices, each lattice corresponding to a received speech utterance associated with filling in one of a plurality of user selected data fields in a user interface, by using at least one speech recognition model; and

a controller that concatenates the plurality of lattices into a single concatenated lattice, and applies the at least one language model to the single concatenated lattice.

9. The rescoring process used in the automatic speech recognition system according to claim 8, wherein the speech utterances are received from a mobile device.

10. The rescoring process used in an automatic speech recognition system according to claim 8, wherein the speech utterances are received from a personal digital assistant.

11. The rescoring process used in an automatic speech recognition system according to claim 8, wherein the rescoring process used in the automatic speech recognition is used in a satellite communications system.

12. The rescoring process used in an automatic speech recognition system according to claim 8, wherein the speech recognition model is a hidden Markov model.

13. The rescoring process used in an automatic speech recognition system according to claim 8, wherein the controller is a network server.

14. A controller used for rescoring results of an automatic speech recognition system, comprising:

a first section that generates a plurality of lattices, each lattice associated with a received speech utterance for filling in one of a plurality of user selected data fields in a user interface;

a second section that concatenates the plurality of lattices into a single concatenated lattice; and

a third section that applies at least one language model to the single concatenated lattice.

15. The controller used for the rescoring results of the automatic speech recognition system according to claim 14, the controller further comprising a fourth section that determines whether an automatic speech recognition process should be performed again.

16. The controller used for the rescoring results of the automatic speech recognition system according to claim 14, wherein the controller is a network server used in a mobile communications system.