Methods and systems for adapting a model for a speech recognition system
First Claim
1. A method for adapting a model for a speech recognition system using an adaptation process, the method comprising:
- with an apparatus using at least one hardware-implemented processor, determining an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words; and
adjusting an adaptation process for the model for the word or various models for the various words, based on the error rate.
3 Assignments
0 Petitions
Accused Products
Abstract
Possible errors made by a speech recognition system may be identified without using a transcript of words input to the system. A method for model adaptation for a speech recognition system includes determining an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The method may further include adjusting an adaptation, of the model for the word or various models for the various words, based on the error rate. An apparatus identifies possible errors made by a speech recognition system without using a transcript of words input to the system. An apparatus for model adaptation for a speech recognition system includes a processor adapted to estimate an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words, without using a transcript of words input to the system. The apparatus may further include a controller adapted to adjust an adaptation of the model for the word or various models for the various words, based on the error rate.
175 Citations
37 Claims
-
1. A method for adapting a model for a speech recognition system using an adaptation process, the method comprising:
-
with an apparatus using at least one hardware-implemented processor, determining an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words; and adjusting an adaptation process for the model for the word or various models for the various words, based on the error rate. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A method for adapting a model for a speech recognition system using an adaptation process, the method comprising:
-
with an apparatus using at least one hardware-implemented processor, generating a count of occurrences of when a user provides feedback to the system; and adjusting an adaptation process for the model based on the count of feedback occurrences. - View Dependent Claims (14, 15, 16, 17, 18)
-
-
19. An apparatus for adapting a model for a speech recognition system using an adaptation process, the apparatus comprising:
-
a processor that is operable to determine an error rate, corresponding to either recognition of instances of a word or recognition of instances of various words among a set of words; and a controller that is operable to adjust an adaptation process for the model for the word or various models for the various words, based on the error rate. - View Dependent Claims (20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30)
-
-
31. An apparatus for adapting a model for a speech recognition system using an adaptation process, the apparatus comprising:
-
a processor that is operable to generate a count of occurrences of when a user provides feedback to the system; and a controller that is operable to adjust an adaptation process for the model based on the count of feedback occurrences. - View Dependent Claims (32, 33, 34, 35, 36, 37)
-
Specification