Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
1999-04-13
2003-07-08
Chawan, Vijay (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S243000, C704S257000, C704S255000
Reexamination Certificate
active
06591236
ABSTRACT:
CROSS REFERENCE TO RELATED APPLICATIONS
Not Applicable
STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT
Not Applicable
BACKGROUND OF THE INVENTION
1. Technical Field
This invention relates to the field of computer speech recognition and more particularly to a method and system for informing a system user of available and alternative speech commands.
2. Description of the Related Art
Speech recognition is the process by which an acoustic signal received by microphone is converted to a set of text words by a computer. These recognized words may then be used in a variety of computer software applications for purposes such as document preparation, data entry and command and control. Speech recognition is generally a difficult problem due to the wide variety pronunciations, individual accents and speech characteristics of individual speakers.
One of the difficult aspects of speech recognition systems relates to a user's ability to navigate through the speech-enabled application using various commands and controls. In the simplest possible command and control grammar, each function that the system can perform has no more than one speech phrase associated with it. At the other extreme is a command and control system based on natural language understanding (NLU). In an NLU system, the user can express commands using natural language, thereby providing total linguistic flexibility in command expression. Current command and control systems are moving beyond the simple one function—one speech phrase grammar, but will not achieve NLU in the foreseeable future.
For systems that approach but do not achieve the flexibility of NLU, it is possible that a user may wish to gain a better understanding of the speech commands which are available. For example, it is possible that a given user may want to know whether a particular speech command will be recognized. Alternatively, a user who knows one way of issuing a speech command might want to know the other ways that he or she could issue speech commands to achieve the same system function or operation. This desire might come from simple curiosity, or might arise from a desire to determine a more efficient speech command or a desire to try out speech commands that have a better recognition accuracy for that user than the speech command that he or she has been using.
Conventional speech recognition systems offer various means to present the user with a list of all valid speech commands, typically filtered in some way to facilitate a search for a particular command. This approach works reasonably well given fairly simple command and control grammars. However, as command and control grammars begin to approach NLU, the number of available ways to state commands increases to the point of making such approaches cumbersome. Thus, there has arisen a need to provide more effective systems and methods for informing a system user of available and alternative speech commands.
SUMMARY OF THE INVENTION
The invention concerns a method and system for efficiently identifying valid system command in a speech recognition system. The method of the invention involves a plurality of steps including: receiving data representative of a speech recognition system user input; comparing the data to a grammar defined for the speech recognition system to determine whether the data is representative of a user input which is a valid system command; and notifying the user as to whether the data is representative of a valid system command. Further, the method can include the additional steps of: determining a functional expression for the data; and comparing the functional expression to a set of all functional expressions permitted in the grammar to identify any alternate user inputs for producing the functional expression.
According to one aspect of the invention, the process can include notifying the user of the alternate user inputs for producing the functional expression and listing the alternate user inputs in sequence based upon a criteria. For example, the criteria can be the order in which the alternate user inputs were identified in the search, alphabetical order, length, recognition accuracy, and a user preference. In the case where there are not other alternative user inputs, the method can include the step of notifying the user that there exist no alternate user inputs for producing the functional expression. Although the method can employ any suitable programming for searching out alternative user inputs to achieve the same functional result, one advantageous method for accomplishing this result is by searching a set of translation rules to identify the functional expression and the alternate user inputs.
According to a second aspect, the invention can be a computer speech recognition system for efficiently identifying valid system commands to users. In that case, the system includes interface programming for receiving data representative of a speech recognition system user input; processor programming for comparing the data to a grammar defined for the speech recognition system to determine whether the data is representative of a user input which is a valid system command; and display programming for notifying the user as to whether the data is representative of a valid system command. The system also preferably includes function determining programming for determining a functional expression for the data; and function comparison programming for comparing the functional expression to a set of all functional expressions permitted in the grammar to identify any alternate user inputs for producing the functional expression. The function determining programming can preferably include programming for searching a set of translation rules to identify the functional expression and the alternate user inputs.
Similar to the previously described method, the system display programming further comprises programming for notifying the user of the alternate user inputs for producing the functional expression and programming for listing the alternate user inputs in sequence based upon criteria selected from the group consisting of: the order in which they were identified in the search, alphabetical order, length, recognition accuracy, and a user preference. Finally, the system display programming can further include programming for notifying the user that there exist no alternate user inputs for producing the functional expression.
According to a third aspect, the invention may comprise a machine readable storage, having stored thereon a computer program having a plurality of code sections executable by a machine for causing the machine to perform a series of steps. These steps can include: receiving data representative of a speech recognition system user input; comparing the data to a grammar defined for the speech recognition system to determine whether the data is representative of a user input which is a valid system command; and notifying the user as to whether the data is representative of a valid system command. The machine readable storage may cause the machine to perform additional steps such as determining a functional expression for the data; and comparing the functional expression to a set of all functional expressions permitted in the grammar to identify any alternate user inputs for producing the functional expression. The machine readable storage can also be programmed for causing the machine to perform the further step of notifying the user of the alternate user inputs for producing the functional expression. As previously described relative to the method and system of the invention, the machine readable storage can similarly be arranged for causing the machine to perform the further step of listing alternate user inputs in sequence based upon specified criteria.
REFERENCES:
patent: 4864623 (1989-09-01), Van Nes et al.
patent: 5255386 (1993-10-01), Prager
patent: 5748841 (1998-05-01), Morin et al.
patent: 5915001 (1999-06-01), Uppaluru
patent: 5937385 (1999-08-01), Zadrozny et al.
patent: 6073102 (2000-06-01), Block
patent: 6119085 (2000-09-01),
Lewis James R.
Ortega Kerry
Chawan Vijay
International Business Machines - Corporation
Senterfitt Akerman
LandOfFree
Method and system for determining available and alternative... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and system for determining available and alternative..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and system for determining available and alternative... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3042108