System and method for improving speech recognition accuracy using textual context

Patent metadata

Field	Value
Publication number	US-9911437-B2
Application number	US-201615146283-A
Country	US
Kind code	B2
Filing date	May 4, 2016
Priority date	Oct 23, 2009
Publication date	Mar 6, 2018
Grant date	Mar 6, 2018

Abstract

Disclosed herein are systems, methods, and computer-readable storage media for improving speech recognition accuracy using textual context. The method includes retrieving a recorded utterance, capturing text from a device display associated with the spoken dialog and viewed by one party to the recorded utterance, and identifying words in the captured text that are relevant to the recorded utterance. The method further includes adding the identified words to a dynamic language model, and recognizing the recorded utterance using the dynamic language model. The recorded utterance can be a spoken dialog. A time stamp can be assigned to each identified word. The method can include adding identified words to and/or removing identified words from the dynamic language model based on their respective time stamps. A screen scraper can capture text from the device display associated with the recorded utterance. The device display can contain customer service data.

First claim

What is claimed is:

1. A method comprising:
identifying, by a processing system including a processor, words in textual content that are relevant to a recorded utterance based on references within the textual content, to yield identified words;
associating, by the processing system, the identified words with a speech recognition model to generate a modified speech recognition model;
removing a word of the identified words from the modified speech recognition model according to an end time stamp assigned to the word; and
recognizing, by the processing system, the recorded utterance using the modified speech recognition model.

2. The method of claim 1 , wherein the references comprises information associated with a product or a service.

3. The method of claim 2 , wherein the textual content is presented on a display of an agent interacting with a user to assist in a purchase of the product or service.

4. The method of claim 1 , wherein the references are associated with social media content.

5. The method of claim 1 , wherein the recorded utterance is a portion of a spoken dialog.

6. The method of claim 1 , wherein each word in the identified words is assigned a beginning time stamp and the end time stamp, and wherein the associating the identified words comprises adding each word to the modified speech recognition model according to the beginning time stamp assigned to each word.

7. A system, comprising:
a processing system including a processor; and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, comprising:
generating identified words by detecting words in textual content that are relevant to a recorded utterance based on external references included in the textual content;
adding the identified words to a speech recognition model to generate a modified speech recognition model;
removing a word of the identified words from the modified speech recognition model according to an end time stamp assigned to the word; and
identifying the recorded utterance using the modified speech recognition model.

8. The system of claim 7 , wherein the external references comprises information relating to a product or a service.

9. The system of claim 8 , wherein the textual content is presented on a display during a purchase of the product or service.

10. The system of claim 7 , wherein the external references are associated with media content.

11. The system of claim 7 , wherein the recorded utterance is a portion of a speech dialog.

12. The system of claim 7 , wherein each word in the identified words is assigned a beginning time stamp and an end time stamp.

13. The system of claim 12 , wherein the adding the identified words comprises adding each word to the modified speech recognition model according to the beginning time stamp assigned to each word, and wherein the operations further comprise removing each word from the modified speech recognition model according to the end time stamp assigned to each word.

14. A non-transitory machine-readable storage medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, comprising:
generating identified words based on a display of textual content that is relevant to a recorded utterance, the textual content including references to external data;
linking the identified words to a speech recognition model to generate a modified speech recognition model;
removing a word of the identified words from the modified speech recognition model according to an end time stamp assigned to the word; and
interpreting the recorded utterance using the modified speech recognition model.

15. The non-transitory machine-readable storage medium of claim 14 , wherein the external data comprises information relating to a product or a service.

16. The non-transitory machine-readable storage medium of claim 15 , wherein the text is presented on a display to assist in a purchase of the product or service.

17. The non-transitory machine-readable storage medium of claim 14 , wherein the external data is associated with media content.

18. The non-transitory machine-readable storage medium of claim 14 , wherein the recorded utterance comprises speech content.

19. The non-transitory machine-readable storage medium of claim 14 , wherein each word in the identified words is assigned a beginning time stamp, and wherein the linking the identified words comprises adding each word to the modified speech recognition model according to the beginning time stamp.

Assignees

• Nuance Communications Inc

Inventors

• Melamed Dan
• Bangalore Srinivas
• Johnston Michael

Classifications

• G06F3/162

  Interface to dedicated audio devices, e.g. audio drivers, interface to CODECs · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L17/04

  Training, enrolment or model building · CPC title

• G10L15/183

  using context dependencies, e.g. language models · CPC title

• G10L15/07

  to the speaker · CPC title