Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
2000-12-12
2003-12-02
Chawan, Vijay (Department: 2655)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
C704S270100, C704S235000, C704S243000, C704S275000, C345S215000, C345S215000
Reexamination Certificate
active
06658386
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 driven user interfaces, and more particularly, to speech based computer driven user interfaces.
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. Improvements to speech recognition systems provide an important way to enhance user productivity.
Speech recognition systems also can function as a user interface to another computer based system. As such, speech recognition systems enable users to interact with computer based systems in a more natural and less mechanistic manner. A common example of a speech interface can be a speech menu interface for enabling an end user to verbally select an item from an audible set of prompts or speech menu items. A speech menu interface typically operates over a communication connection, such as a conventional telephone connection, to provide end users with a series of menu items from which to choose. For example, a speech menu interface can be incorporated within a system for routing incoming telephone calls based on an end user specified call destination.
Speech menu interfaces can be implemented using several different methods. One method is to associate each menu item with a numeric value which the user can choose by speaking the number into the telephone or pressing the corresponding number button on the telephone. Such implementations, called representative style presentation, are beneficial when the speech menu items are long, complex, or difficult to remember. For example, a speech menu interface can present the following items to an end user: “For the Communications Product Hardware and Software Department press 1, For the Personal Computer Product Department including Hardware and Software press 2”. Notably, the department names among which the end user is choosing are long and difficult to remember. By providing a numeric value associated with each item, the end user need only remember the number associated with the desired item rather than the entire item name.
Another method of implementing a speech interface is to allow the end user to directly speak the desired item into the telephone. This implementation, called literal style presentation, is beneficial when the menu items are short, less complicated, or easier to remember. Notably, literal style presentation can be a more desirable and direct method of allowing an end user to choose a menu item. For example, a speech menu interface can provide the following menu items to an end user: “Please say one of the following departments: Marketing, Finance, Human Resources, Accounting”. In this case, the end user need only say a department name for the end user's call to be forwarded to the specified department.
Both representative style presentation and literal style presentation implementations of speech menu interfaces offer advantages. Accordingly, a system designer can plan and implement the proper speech interface in situations where the menu items are known in advance to the designer. However, some computer based systems generate menus dynamically, extracting menu items from a database of possible menu items. In this case, a design decision is made by the system designer even though the menu items which ultimately will be presented to the user are not known. Because the system designer must choose an implementation, i.e., representative style presentation or literal style presentation, without knowing which menu items ultimately will be presented to a user, the resulting speech menu can sound confusing and overly complicated. Thus, the benefits of a speech menu interface can be lost.
SUMMARY OF THE INVENTION
The invention concerns a method for adjusting a speech menu interface as a function of attributes of speech menu items or prompts. The method of the invention can select a presentation style for presenting speech menu items after dynamically selecting the speech menu items from a database of possible speech menu items. The selection of a presentation style can be based upon speech menu item attributes corresponding to the complexity of a speech menu item. Speech menu item complexity can correspond to the level of difficulty experienced by users in pronouncing the speech menu item or in remembering the speech menu item. Thus, the attributes can reflect complexity indicators such as length information of speech menu items, length information of individual text strings within speech menu items, or both. Additional complexity indicators can include whether the menu item includes acronyms, foreign words, words of art such as medical or legal terms, or any words determined through an empirical study to be complex. Based on the speech menu item attributes, a presentation style can be selected for presenting the items through the speech menu interface.
The inventive method taught herein can begin by identifying one or more speech menu items (menu items) from a data structure in memory for presentation using the speech menu interface. The method further can include retrieving the one or more menu items from the data structure. The step of reading at least one attribute corresponding to the menu items can be included. Notably, the method can include determining the attributes corresponding to the menu items. The attributes can be a binary indicator or a score corresponding to the complexity of the menu items. The reading step can include comparing the attributes corresponding to the menu items with menu item criteria. Notably, the menu item criteria can be one or more threshold values. Based on the reading step, the method can include selecting a presentation style for presentation of the one or more menu items using the speech interface. The presentation style can be literal style presentation or representative style presentation. Further, the method can include presenting the one or more menu items through the speech menu interface using the selected presentation style.
Another embodiment of the invention can be a method of adjusting a speech menu interface. In that case, the method can include identifying one or more menu items from a data structure in memory for presentation using the speech menu interface. The step of retrieving one or more menu items from the data structure can be included. The additional step of reading at least one attribute corresponding to the menu items can be included. The reading step also can include comparing the attributes with menu item criteria, where the menu item criteria can include one or more threshold values. Based on the reading step, the method can include selecting a presentation style for presentation of the one or more menu items using the speech menu interface. Additionally, the step of presenting the one or more menu items through the speech menu interface using the selected presentation style can be included.
Another aspect of the invention can be 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. The steps can include identifying one or more menu items from a data structure in memory for presentation using the speech menu interface. The step of retrieving the one or more menu items from the data structure and reading at least one attribute corresponding to the menu items can be included. Notably, the step of determining the attributes corresponding to the menu items can be included. The attributes can include a binary indicator or a score corresponding to the complexity of the menu items. The reading step can include comparing the attributes corresponding to the menu items with menu item cri
Kemble Kimberlee A.
Lewis James R.
Michelini Vanessa V.
Zabolotskaya Margarita
Akerman & Senterfitt
Chawan Vijay
International Business Machines - Corporation
Nolan Daniel A.
LandOfFree
Dynamically adjusting speech menu presentation style does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Dynamically adjusting speech menu presentation style, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Dynamically adjusting speech menu presentation style will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3131198