EP0651372A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Automatic speech recognition (ASR) processing using confidence measures
Assignee: AT&T Inc
•
Filing: 1994-10-19
•
Granted: —
•
Expires: 2014-10-19
Abstract
Abstract The user interface in an automatic speech recognition (ASR) system is is dynamically controlled, based upon the level of confidence in the results of the ASR process. In one embodiment, the system is arranged to distinguish error prone ASR interpretations from those likely to be correct, using a degree of confidence in the output of the ASR system determined as a function of the difference between the confidence in the "first choice" selected by the ASR system and the confidence in the "second choice" selected by the ASR system. In this embodiment, the user interface is arranged so that the explicit verification steps taken by the system as a result of uncertain information is different from the action taken when the confidence is high. In addition, different treatment can be provided based upon the "consequences" of misinterpretation as well as the historical performance of the system with respect to the specific user whose speech is being processed. In another embodiment, after an ASR system interprets an utterance, the confidence in the interpretation is assessed, and three different interactions with the user may then occur.
Inventors
- 👤 Douglas J. Brems
- 👤 Max S. Schoeffler
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-31 13:15
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/22; G10L15/08; G10L15/10
Claims Analysis
Total Claims: 21
Claim 1
Independent Claim
70 words
A system for adapting the user interface in systems that accept speech input and perform automatic speech recognition (ASR), comprising means for receiving an utterance; means for processing said utterance using ASR to generate an interpretation of said utterance and to determine a level of confidence in said interpretation; and means for selectively adapting the verification of said interpretation requested from the user as a function of said confidence level.
Claim 2
Dependent Claim
54 words
The invention defined in claim 1 wherein said processing means is arranged to determine at least first and second interpretations for said utterance, said interpretations having respective associated first and second confidence values, and wherein said confidence level is determined as a function of the relative magnitudes of said first and second confidence values.
Claim 3
Dependent Claim
60 words
The invention defined in claim 1 wherein said system further includes means for storing, for each user of said system, information representing a success measure computed as a function of previous uses of said system, and means for retrieving information from said storing means and for adapting said user interface as a function of the value of said success measure.
Claim 4
Dependent Claim
22 words
The invention defined in claim 3 wherein said success measure includes the previous success rate for said each user of said system.
Claim 5
Dependent Claim
22 words
The invention defined in claim 3 wherein said success measure includes previous confidence values associated with ASR interpretations for said each user.
Claim 6
Dependent Claim
21 words
The invention defined in claim 3 wherein said system is arranged to compare said success measure to a user dependent threshold.
Claim 7
Dependent Claim
29 words
The invention defined in claim 1 wherein said last mentioned means is arranged to adapt said verification as a function of the consequences of an error in said interpretation.
Claim 8
Dependent Claim
67 words
An automatic speech recognition system comprising means for generating at least first and second interpretations of a user's utterance and respective first and second confidence values for said interpretations, and means operative in response to the relative magnitudes of said first and second confidence values, for prompting said user to verify said first interpretation prior to accepting said first interpretation as an accurate representation of said utterance.
Claim 9
Dependent Claim
22 words
The invention defined in claim 8 wherein said system further includes means for prompting said user with information including said first interpretation.
Claim 10
Dependent Claim
71 words
An automatic speech recognition system comprising means for generating an interpretation of a user's utterance and a confidence value for said interpretation, and user interface means operative in response to the magnitude of said confidence value, for (a) requesting said user to verify said interpretation prior to accepting said interpretation as an accurate representation of said utterance, or (b) accepting said interpretation as an accurate representation of said utterance without verification.
Claim 11
Dependent Claim
43 words
The invention defined in claim 10 wherein said system further includes means for storing information indicative of the previous success of said system in interpreting utterances of said user, and means for responsive to said stored information for controlling said user interface means.
Claim 12
Independent Claim
67 words
A method of adapting the user interface in systems that accept speech input and perform automatic speech recognition (ASR), comprising the steps of receiving an utterance; processing said utterance using ASR to generate an interpretation of said utterance and to determine a level of confidence in said interpretation; and selectively adapting the verification of said interpretation requested from the user as a function of said confidence level.
Claim 13
Dependent Claim
45 words
The method defined in claim 12 wherein said processing step includes determining at least first and second interpretations for said utterance, said interpretations having respective associated first and second confidence values, and determining confidence level as a function of said first and second confidence values.
Claim 14
Dependent Claim
48 words
The method defined in claim 12 further including storing, for each user of said system, information representing a success measure computed as a function of previous uses of said system, and retrieving information and altering the user interface as a function of the value of said success measure.
Claim 15
Dependent Claim
22 words
The method defined in claim 14 wherein said success measure includes the previous success rate for said each user of said method.
Claim 16
Dependent Claim
22 words
The method defined in claim 14 wherein said success measure includes previous confidence values associated with ASR interpretations for said each user.
Claim 17
Dependent Claim
20 words
The method defined in claim 14 wherein said method further includes comparing said success measure to a user dependent threshold.
Claim 18
Independent Claim
66 words
A method of automatic speech recognition comprising the steps of generating at least first and second interpretations of a user's utterance and respective first and second confidence values for said interpretations, and in response to the relative values of said first and second confidence values, prompting said user to verify said first interpretation prior to accepting said first interpretation as an accurate representation of said utterance.
Claim 19
Dependent Claim
20 words
The method defined in claim 18 wherein said method further includes prompting said user with information including said first interpretation.
Claim 20
Independent Claim
91 words
A method for performing automatic speech recognition system comprising the steps of generating an interpretation of a user's utterance and a confidence value for said interpretation, and adapting the operation of a user interface in response to the magnitude of said confidence value, by (a) requesting said user to verify said interpretation prior to accepting said interpretation as an accurate representation of said utterance, (b) accepting said interpretation as an accurate representation of said utterance without verification, or (c) rejecting said interpretation and requesting said user to provide a new utterance.
Claim 21
Dependent Claim
41 words
The method defined in claim 20 wherein said method further includes the steps of storing information indicative of the previous success of said system in interpreting utterances of said user, and adapting said user interface in response to said stored information.
References Cited (Backward Citations)
US4922519A
Cited
US4827500A
Cited
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.