System and method for customizing speech recognition input and output
First Claim
1. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
- collecting data having a predetermined format;
displaying the data to a user for review;
categorizing the data according to user specified data rules;
outputting the categorized data to a language model;
determining final report formats according to said user specified format rules;
determining a level of logging information; and
outputting the final report formats and the level of logging information to a post processor.
8 Assignments
0 Petitions
Accused Products
Abstract
5 A system and method may be disclosed for facilitating the site-specific customization of automated speech recognition systems by providing a customization client for site-specific individuals to update and modify language model input files and post processor input files. In customizing the input files, the customization client may provide a graphical user interface for facilitating the inclusion of words specific to a particular site. The customization client may also be configured to provide the user with a series of formatting rules for controlling the appearance and format of a document transcribed by an automated speech recognition system.
149 Citations
69 Claims
-
1. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
-
collecting data having a predetermined format;
displaying the data to a user for review;
categorizing the data according to user specified data rules;
outputting the categorized data to a language model;
determining final report formats according to said user specified format rules;
determining a level of logging information; and
outputting the final report formats and the level of logging information to a post processor. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
-
collecting data having a predetermined format;
displaying the data to a user for review;
categorizing the data according to user specified data rules; and
outputting the categorized data to a language model. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
-
collecting data having a predetermined format;
displaying the data to a user for review;
determining final report formats according to user specified format rules; and
outputting the final report formats to a post processor. - View Dependent Claims (16, 17, 18, 19, 20)
-
-
21. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
-
collecting data having a predetermined format;
displaying the data to a user for review;
determining a level of logging information; and
outputting the level of logging information to a post processor. - View Dependent Claims (22, 23, 24, 25, 26)
-
-
27. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
-
collecting data having a predetermined format;
displaying the data to a user for review;
categorizing the data according to user specified data rules;
outputting the categorized data to a language model; and
determining a level of logging information. - View Dependent Claims (28, 29, 30, 31, 32, 33)
-
-
34. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
-
collecting data having a predetermined format;
displaying the data to a user for review;
determining final report formats according to user specified format rules;
determining a level of logging information; and
outputting the final report formats and the level of logging information to a post processor. - View Dependent Claims (35, 36, 37, 38, 39)
-
-
40. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
-
collecting data having a predetermined format;
displaying the data to a user for review;
categorizing the data according to user specified data rules;
outputting the categorized data to a language model;
determining final report formats according to user specified format rules; and
outputting the final report formats to a post processor. - View Dependent Claims (41, 42, 43, 44, 45, 46)
-
-
47. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
-
collecting words in an add words interface;
categorizing the words into user defined categories;
outputting word files of the categorized words, the word files corresponding to the user defined categories;
determining formatting rules in a formatting rules interface;
customizing a language model by including the word files for input to the speech recognition engine; and
customizing a delta file by including the formatting rules for input to a post processor. - View Dependent Claims (48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66)
-
-
67. A method for customizing the input and output of a speech recognition engine, the method comprising the steps of:
-
collecting words in an add words interface;
categorizing the words into user defined categories;
generating word files of the categorized words, the word files corresponding to the user defined categories;
determining formatting rules in a formatting rules interface;
customizing a language model by including the word files for input to the speech recognition engine;
customizing a delta file containing the formatting rules for input to a post processor; and
capturing transcriptionist corrections in a file for input to the add words interface.
-
-
68. A customization system comprising:
-
a customization client including an add words interface and a formatting rules interface;
the add words interface for collecting words and categorizing the words into user defined categories;
the formatting rules interface for determining user defined formatting rules;
wherein the add words interface generates word files according to the user defined categories and provides the word files to a speech recognition engine, and the formatting rules interface generates a delta file of the user defined rules and provides the delta file to a post processor.
-
-
69. A system for customizing speech recognition input and output, the system comprising:
-
at least one processor;
a memory coupled to the at least one processor;
a language model for input into a speech recognition engine;
a delta file for input into a post processor;
a customization client configured to be stored as a computer programmable readable media in the memory and to be executed by the at least one processor, wherein the customization client is configured to include an add words interface and a formatting rules interface, the add words interface being configured to receive and categorize data according to a user'"'"'s input, the add words interface also being configured to generate data files for inclusion into the language model, the formatting rules interface being configured to determine formatting rules according to the user'"'"'s input, the formatting rules interface also being configured to generate the delta file.
-
Specification