Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
1998-10-20
2003-07-22
To, Doris H. (Department: 2655)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S277000
Reexamination Certificate
active
06598016
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention is directed to a system for using speech recognition with map data.
2. Description of the Related Art
The computer has revolutionized the idea of a map from an image statically depicting the location of physical, political, or other features to the electronic map, which consists of geographically referenced electronic data quantifying a physical, social or economic system. The range of information included in electronic maps is unlimited. For example, an electronic map of roads could include distances between elements, travel time, lot numbers, tax information, tourist information, processing time, waiting time, etc. Additionally, storing a map as one or more intelligent data files on a computer allows for unlimited software applications to manipulate that data.
One advantage of the electronic map is that it can store and determine costs associated with various portions of a map. A cost is a variable that can be minimized or maximized. Examples of costs include time, distance, tolls paid, ease of turning, quality of scenery, etc. Typically costs are represented as integers. Sometimes costs can be represented as real numbers or non-standard numbers. Additional information about costs and non-standard numbers can be found in U.S. patent application Ser. No. 08/756,263, “Using Multiple Levels Of Costs For A Pathfinding Computation,” filed Nov. 25, 1996, incorporated herein by reference.
Electronic maps can be used for pathfinding, which is a method for computing a route between an origin and a destination. Some systems compute recommended routes and guide the driver by highlighting the recommended route on a map display, or by giving turn-by-turn directions (via paper or display), or both. When a pathfinding system is computing a recommended route to a destination, it does so by finding the most desirable route according to certain specified criteria. These criteria may be specified by the driver, or may be set as defaults at the time of manufacture. Often, a system will be used to find a path that minimizes (or maximizes) some cost, for example, driving time.
An electronic map that is used for pathfinding must carry information about the connectivity of a road network, that is, information about the ways in which pieces of road do or do not connect to each other, for example, where there are ordinary intersections, where there are overpasses, where turns are restricted, and so on. For an area of any significant extent, this is a very large amount of information. An electronic map can include tens or hundreds of megabytes of data. In order to hold such vast quantities of data economically and allow a user to replace maps with updated copies easily, many current pathfinding apparatus (which includes general purpose computers with pathfinding software, automotive navigation systems or other map application equipment) use CD-ROMs to store the electronic map data.
While using electronic maps for pathfinding may be very useful, the complexity of the maps and map tools often require considerable human-machine interaction to achieve a desired result. For example, finding a location on a map or computing a path between two locations may require entering one or more addresses into a computer. This can be time consuming, a distraction or even impossible without the proper equipment. For example, if a system utilizing an electronic map does not include a keyboard, it may be difficult to enter an address. Additionally, if a navigation system is located in an automobile, the driver of the automobile may not be able to enter information into the navigation system while driving. Additionally, traditional systems using electronic maps require the system to be at the same location as the user.
One means for improving systems using electronic maps includes using speech recognition. However, prior art systems which use speech recognition to enable simple human-machine interfaces with map applications have not been very useful. Examples include systems that allow speech recognition for map manipulation commands such as “pan up” or “zoom in.” Other systems allow the identification of general areas, such as stating a city or neighborhood and causing the system to draw a map of that city or neighborhood. Higher resolution geographic functions, such as address location, have been tried only using letter by letter spelling to input a street name. Thus, the prior systems have been limited in their utility to either a small set of commands, a low resolution selection method or a slow and cumbersome interface (e.g., spelling out P-e-n-n-s-y-l-v-a-n-i-a A-v-e-n-u-e is tedious). These systems are also inadequate because of the limit of the dictionary of recognizable words and word combinations processed by the speech recognition.
To make a system easy to use, it would be advantageous to be able to recognize locations in a map by allowing a user to state the address or an intersection; however, there are no systems that provide this function.
SUMMARY OF THE INVENTION
The present invention, roughly described, provides for a system for using speech recognition with map data. The system receives a plurality of speech inputs. The speech inputs include one or more pronounced street names, one or more pronounced numbers and/or one or more pronounced commands. Each speech input is associated with one of a set of two or more speech recognition systems. For each speech input, the system accesses the associated speech recognition system in order to recognize the speech input. The system combines a first recognized street name with either a first recognized number or a second recognized street name to form a description of a first location. The system finds that first location in an electronic map and reports that first location.
In one embodiment, the system combines a third recognized street name with either a second recognized number or a fourth recognized street name to form a description of a second location. The system determines a path from the first location to the second location, and reports that path. Reporting the location includes drawing a map depicting the location, stating the location using a speaker, depicting information about the location using a display, passing information about the location to a hardware device or passing information about the location to a software routine. In one embodiment, the step of reporting the path and the step of reporting the first location are performed together by displaying a map which shows the first location as well as the path from the first location to the second location. Two steps of reporting could also be performed separately. The step of reporting the path can also include providing turn-by-turn directions using a map, text or audio. In addition to displaying a location and finding a path, the system can also be used to perform other functions using the electronic map.
The present invention can be implemented using software, hardware, or a combination of software and hardware. When all or portions of the present invention are implemented in software, that software can reside on a processor readable storage medium. Examples of appropriate processor readable storage medium include one or more floppy disks, hard disks, CD ROMs, memory IC's, etc. When the system includes hardware, the hardware may include an output device (e.g. a monitor), an input device (e.g. a keyboard, pointing device and/or a microphone) a processor in communication with the output device and processor readable storage medium in communication with the processor. The processor readable storage medium stores code capable of programming the processor to perform the steps to implement the present invention. The process of the present invention can also be implemented in a web page on the Internet or on a server that can be accessed over the telephone lines.
These and other objects and advantages of the invention will appear more clearly from the following detailed description in which the preferred embodiment of th
Liu Hongche
Zavoli Walter B.
Fliesler Dubb Meyer & Lovejoy LLP
Opsasnick Michael N.
Tele Atlas North America, Inc.
LandOfFree
System for using speech recognition with map data does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System for using speech recognition with map data, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System for using speech recognition with map data will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3012960