Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
1998-06-29
2002-08-13
{haeck over (S)}mits, Tãlivaldis Ivars (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
C704S235000
Reexamination Certificate
active
06434526
ABSTRACT:
FIELD OF THE INVENTION
The present invention relates to communication networks and more particularly to the provision of a speech recognition capacity to special application program services provided on a network.
BACKGROUND OF THE INVENTION
A small business can easily afford the cost of a personal computer and associated general purpose software such as word processing, spread sheet and database programs. In fact a personal computer bundled with state of the art general purpose software, can be purchased for well under $6000. Those bundled packages usually include free limited time warranties for telephone and on-site services for the hardware and software of the package. Further, extensions of warranties can be purchased at reasonable cost from the manufacturers of the hardware and/or software or from local service providers.
As opposed to the costs involved in the obtaining and maintaining of a computer system with general purpose software, the initial cost and upkeep of specific application software can be prohibitive to the small business entrepreneur, often requiring an initial investment of more than 10 times the cost of the previously mentioned hardware and its bundled general purpose software. services for maintaining the specific application software can be equally expensive and service may not be immediately available.
Because of the expense, many small businesses forego the use of excellent available application specific software and develop their own application specific software. This home based software usually is not as good or reliable as the marketed products. Beside as being saddled with inferior software such a small user must devote a significant amount of time and energy to the development and upkeep of the user developed software.
Speech recognition software, such as IBM's existing Via Voice voice dictation software product, is a tool that can improve work efficiency. For instance, in the field of radiology a large number of patient x-rays are reviewed on a daily basis. Typically, a radiologist will dictate his findings into a tape recorder while reviewing the x-rays. A radiologist may see up to 25 patients a day and have a pressing need to be otherwise productive during the time they are reading x-rays. After the radiologist has dictated, the tape is usually given to a transcriptionist who listens to the entire tape and types a patient report. The turnaround time for a final patient report can take up to 2-3 days. To finish, the transcriptionist may have to stop working to contact the radiologist because the dictation cannot be understood. The turnaround time can be even poorer in large city hospitals where hundreds of x-rays a day are involved. The delay not only impacts the primary care providers, but also affects payments by insurance companies. Radiologists would be better served where the report is accurate the first time so that it can be distributed quickly to individuals who need the information.
With Speech recognition software, such as IBM's MedSpeak/Radiology software for continuous speech recognition, the radiologist can dictate quickly into a microphone connected to his PC and create the report and, if necessary, correct if for accuracy. The radiologist may then choose to send it to a local printer or send a copy of it on-line to those in need of its contents. Radiologists and other physicians can dictate with both hands and eyes free to examine the patient. The reports for patients seen are finalized, completed and sent on-line the day of the examination. In this way, critical information gets in the hands of people waiting for it in a shorter period of time. The radiologist can eliminate large backlogs of uncompleted reports, see more patients and quickly receive compensation for his services.
While speech recognition software with a general purpose dictionary is generally inexpensive, one with a vocabulary for specific applications can be expensive. The cost of a special dictionary, coupled with the cost of other software such as billing software and professional and governmental compliance software, may result in a small user concluding to forego the use of speech recognition. Furthermore, the cost of development of the dictionary for certain fields has been a deterrent where the possible market for sale of the dictionary is not as large as the radiology field.
BRIEF DESCRIPTION OF THE INVENTION
In accordance with the present invention, speech recognition software is provided in combination with application specific software on a communications network. Analog voice data is digitized at a user's location, identified as voice data, and transmitted to the application software residing at a central location. The network server receiving data identified as voice data transmits it to a speech server. Speech recognition software resident at the speech server contains a dictionary and modules tailored to the voice of each of the users of the speech recognition software. As the user speaks, a translation of the dictation is transmitted back to the user's location and appears in text on the user's computer screen for examination and if necessary, voice or typed correction of its contents. Multiple users have interleaved access to the speech recognition software so that transmission back to each of the users is contemporaneous.
With the above arrangement, a fixed or use related monthly rental fee replaces the purchase price and service charges for the software. Since the software is shared by many users, the entry cost for each user is reduced thereby increasing the potential market for the software. Furthermore, since service of the software occurs at the central location, it can be more expeditiously performed reducing software downtime.
Therefore it is an object of the present invention to provide, on a network, specific application software with a speech recognition capability.
It is another object of the invention to provide, on a network, software with speech recognition capability that capacity can be expanded dynamically.
REFERENCES:
patent: 5524169 (1996-06-01), Cohen et al.
patent: 5632002 (1997-05-01), Hashimoto et al.
patent: 5799273 (1998-08-01), Mitchell et al.
patent: 5857099 (1999-01-01), Mitchell et al.
patent: 5909662 (1999-06-01), Yamazaki et al.
patent: 5960399 (1999-09-01), Barclay et al.
patent: 6078886 (2000-06-01), Dragosh et al.
patent: 2 082 820 (1982-03-01), None
patent: 2 323 693 (1998-09-01), None
patent: 2 323 694 (1998-09-01), None
AT&T Advanced Speech Products Group (3 pgs).
Besteam IBM Business Enterprise Solutions Team (4 pgs).
Cilurzo Frank
Miller Roger Matthew
Crockatt J.
International Business Machines - Corporation
{haeck over (S)}mits Tälivaldis Ivars
LandOfFree
Network application software services containing a speech... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Network application software services containing a speech..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Network application software services containing a speech... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2906435