Data processing: speech signal processing – linguistics – language – Speech signal processing – Recognition
Reexamination Certificate
1999-07-08
2001-07-24
Knepper, David D. (Department: 2645)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Recognition
C704S275000, C704S270000
Reexamination Certificate
active
06266635
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of Invention
The invention relates generally to the field of voice directed dictation. More particularly, the invention provides for a system and method for an interactive voice interface.
2. Prior Art
From the very beginning of computer design, the aspirations of the designer have included a voice interaction with the computer. PC applications such as dictation, scheduling, display and voice command interfaces, communications, robotics and industrial controls were felt to be only a few of the many practical uses for such technology. Implementation, however, has been a slow and disappointing process. The spoken word comprises unlimited permutations of sounds, inflections, dialects, languages, volumes as well as the inclusion of ambient and communications related noise.
As technology has progressed, however, so has the ability to decipher the spoken word. In spite of the advancements in voice recognition, the prior art has failed to capitalize on the recent technology available to develop a precise, accurate and easy to use system which, not only recognizes the spoken words, but provides an interactive interface to commands as well as application specific report creation.
Whatever the precise merits, features and advantages of the prior art, it fails to achieve or fulfill the purposes of the present invention. Accordingly, it is an object of the present invention to provide for an interactive voice interface.
It is another object of the present invention to provide for a voice interface capable of multitasking.
It is an additional object of the present invention to develop an interactive voice activated question and answer session.
It is an additional object of the present invention to include commands in the interactive question and answer session.
It is an additional object of the present invention to enable a user to create a report during clinical procedures using prerecorded database entrees correlated with spoken words and commands.
These and other objects are achieved by the detailed description that follows.
SUMMARY OF THE INVENTION
A dictation and command voice multitasking interface is implemented by the creation of a question and multiple answer database. The system is responsive to spoken words first recognized and then correlated with the previously recorded questions, commands or tasks. The system is interactive with the speaker, in a typical question and answer(Q&A) session until the completion of the task at hand. Various salient elements include: timed dictation periods, silent period detection, multimedia applications; as well as multitasking to include mixtures of Q&A, commands and a variety of tasks.
In the preferred embodiment, the system is essentially set up for use by a physician and facilitates the creation of clinical reports (e.g., those used by a surgeon). Typically, a surgeon will perform a limited number of types of procedures. Each of the procedures performed requires a report to be done soon thereafter. A considerable amount of the report is a “boiler plate” including stock paragraphs such as the description of a disease, a description of the surgery, a description of the procedure, etc. In addition, certain particular items are related to the particular operation but are limited to specific types of information. For example, the number of sutures put in, the length of the cut, etc.
During the operation it is difficult for the surgeon to make use of their hands but their voice is readily available for dictating information with respect to the procedure. They can also use their voice for issuing commands such as “take a picture”, “take an x-ray”, “phone another doctor”, etc.
The present invention permits the user to utilize their voice to dictate information which will be used as part of their report, to answer specific questions that are preset with fixed preset type answers, to issue commands such as taking a photograph, making a phone call, etc., all with the same system. Thereafter, the report will essentially be formatted by the system with all of the preset paragraphs, any unique paragraphs that the user has set in himself, as well as taking the answers to the questions and fitting them in appropriately to preset paragraphs. Thus, the final report will be automatically prepared. Of course, it can be edited by the user at any time on the computer.
Initially, the user must spend a little time with the system, training it to recognize their voice and setting up their own questions and answers. Each user has a different voice and therefore the system must be trained to accommodate each user's voice.
The system is also preset in various ways. Firstly, with respect to ongoing dictation during the procedure, it is set to limit the length of a dictation. For example, the user may issue the voice command to “start dictation”. The machine will then turn on the receiver and give the user a preset period of 28 seconds, for example, to dictate. After this period has expired the system will either verbally or in writing tell the user the dictation is over. The user must then reinstitute the command if additional dictation is required. This is typical, for example, a surgeon will only dictate short statements during a procedure.
The system is also set to check on fixed periods of silence. After a voice is detected, it has a preset amount of time whereby it expects additional words. The length of these silent periods are prefixed.
Initially when a user wants to set up the system, they enter the system, put in their name, and identify a particular procedure that is to be set up. For example, a doctor might enter “gall bladder”. At that point, the system will bring up prerecorded paragraphs relating to the “gall bladder” and they can select which ones they want to make use of. They may also want to enter their own “boiler plate” paragraphs regarding aspects of gall bladder operations in general.
The user begins by setting up the voice aspects of the program. They then begin by printing a particular question relating to the procedure. Thereafter the question is recorded. They then proceed to print the individual answers that can be given which are recorded individually.
REFERENCES:
patent: 5420912 (1995-05-01), Kopp et al.
patent: 5519808 (1996-05-01), Benton, Jr. et al.
patent: 5812977 (1998-09-01), Douglas
patent: 5884266 (1999-03-01), Dvorak
Contec Medical Ltd.
Helfgott & Karas P.C.
Knepper David D.
LandOfFree
Multitasking interactive voice user interface does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Multitasking interactive voice user interface, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multitasking interactive voice user interface will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2477136