|
Number 51,
June 2006
PRICING FOR WEB-BASED
COMMAND!™
The company has received several inquiries about
web updates for
Command!™. Web-based Command!™ includes options for web services, web transfer server, and
web application. The
new web services and web transfer server may be used in place of the job
transfer server that relied upon email or FTP.
This update is FREE to all existing
Command!™
licensees.
New features also include a browser-based web
application that permits manual upload and download of job files and manual
editing of works in progress. The add-in application includes a single license for
web services. Pricing for the web application is based upon the number
of concurrent sessions and is available
here. Web
services includes web services, web server, and
configuration tool. Web services may run with web server or
Microsoft Information Internet Services (IIS). One separate web
transfer server is required for each separate Command! database.
OTHER
UPGRADES
SpeechMax™ upgrades involve multiple
changes, including multiwindow and
multilingual capability, integration with transcriptionist footpedal,
plugins for text to speech and real-time and file-based speech recognition,
voice recording, insertion of pictures and graphics, and more. See
the information below. SpeechServers™
has been upgraded to run with
newer version of Dragon NaturallySpeaking®
v. 8.1 and SAPI 5.x speech engines, such as the FREE Microsoft speech engine.
As before, the IBM ViaVoice v. 10 does not require a speaker
enrollment. Dragon requires speaker client enrollment but the speech
user profile can be easily transferred to the central server.
SPEECHMAX™--MORE
THAN A WORD PROCESSOR™
As the summary from the recent For the Record article below
indicates, generation of true savings from speech recognition in health care
requires creation of new efficiencies, not just shifting the burden of
transcription and correction from the hospital transcriptionist employees to
physicians. As the article indicates, many physicians are reluctant to
use speech recognition because it requires them to change dictation habits,
or to spend time correcting the inevitable mistakes that result from speech
recognition. Even with a 5% error rate, this works out to a mistake in
just about every other sentence, a task that few physicians are eager to
undertake. However, U.S. and foreign patented and patents
pending SpeechMax™,
is designed to create both front-end and back-end efficiencies. For
example, SpeechMax™
may be used as a graphical user interface and editor for real-time speech
recognition with Dragon NaturallySpeaking®
Professional, Medical, or Legal and other speech recognition engines.
As indicated by ad the appearing with the For the Record article, the
session file can be sent for deferred correction by a transcriptionist using
a standard, three-position foot control in SpeechMax™,
or the audio can be exported as a separate WAV
file for correction with a foot control and use of a standard word processor
such as Word or WordPerfect. Click
here to view the
ad. Using a runtime license, the software provides the "essentials"
for speech recognition for dictation and a substantial savings compared to
standard "out-of-the-box" or other solutions. The SpeechMax™
software also supports structured dictation by the physician into fields
(e.g., for patient name, type of exam, and so on) as well as continuous
audio dictation. The software also permits the user to save text and
dictation audio from manual transcription to create or train speech user
profiles for Dragon, IBM, or SAPI 5.x (including Microsoft) speech
recognition, and advanced text comparison with audio playback for transcription
QA, and other purposes. It also includes many other interesting and useful features,
including digital scrapbooking with addition of voice or music annotations
or text comments created with speech recognition using Dragon
NaturallySpeaking® or other speech engines.
Click here to view Key Features.
SPEECH SOLUTIONS--INTEGRATION WITH RADIOLOGY PACS
CustomMike™
is an easily-customizable sound recorder that has been used for a wide
variety of applications, including digital dictation in medical and law
practices. One customer, a
pathology group, has used the sound recorder for hands-free dictation
during microscopic or gross dissections. An
in-house legal department for a large real estate development and signage
company uses it to record dictation before manual transcription.
Another customer, purchaser of the CustomMike™
SDK, is integrating the sound recorder with web-based radiology picture
and archival (PACS) and radiology information (RIS) systems for use with
Philips SpeechMike.
SAVINGS FROM SPEECH
RECOGNITION IN HEALTH CARE
Speech recognition may be used interactively, real-time with the speaker
correcting and editing the transcribed text and completing the document in
one step. In another approach, back-end, server-based recognition typically
results in editing by transcriptionists, though it may be returned to
physicians alone for correction. Deferred speech recognition requires change
primarily in transcription, not the dictating physicians. Generally, the
ultimate decision to use front-end or back-end speech recognition depends
upon the amount of change that a hospital's physicians are willing to
accept. A 2004 survey of health information managers showed that 26% were
using speech recognition. In a 2005 survey, 59% of health information
technology executives said they planned to implement the technology within
the next two years. In the $22 billion medical transcription with more than
$6 billion spend on labor, at 25% reduction in costs could result in $1.5
billion in savings. Hospitals realize savings from speech recognition from
reducing in-house and outsourced transcription. One estimate is that 10% to
15% of radiology practices and 20% of pathologists use speech recognition,
with 25% and 20% evaluating speech recognition for implementation within a
year. Savings result because it is faster to edit than to type, and much of
the editing and proofing has been shifted to physicians, especially those
who are using real-time speech recognition. Further savings accrue from
implementation of workflow software that reports physician turnaround time
and provides more accessible review and sign-off, often through web-based
systems. Start-up costs are variably estimated at $900 out of box, or less
than $3,000 in the first year including training, support, and maintenance,
to $4,000 to $10,000 per user, with lower costs in subsequent years. E.
S. Roop, "Speaking of Savings: Can Speech Recognition Deliver?," For the
Record (May 15, 2006)
SPEECH RECOGNITION NOW
MAINSTREAM
A recent article in VARBusiness indicates that speech recognition has
lost its reputation as a "handicapped" technology with low accuracy rates
and poor performance. Long used for those with disabilities, speech
recognition is now going mainstream. As indicated in the article,
speech-recognition market consists of embedded applications, telephony, and
dictation. The most active is dictation. The solution-provider
contribution is important since speech-recognition requires a great deal of
customization. "There's a large opportunity for individuals interested
in adding value to the basic speech-recognition technology that's currently
available," says Bill Wade, vice president of St. Louis-based Kaberline
Healthcare Informatics, a physician-owned speech reseller that targets
medical, veterinary, legal, and corporate markets. Wade further
indicates that Kaberline has customized products to help medical facilities
jump-start the digitization of medical records. "There's less need for
box-pushers than there is for people with an eye toward the development of
innovative ways to incorporate speech recognition into the expanding
workflow of today's business." But, ultimately, VARs are likely to
benefit most from the fact that speech recognition requires a great deal of
training and customer hand-holding. "Without solid training, in fact,
about half of all users outfitted with speech-recognition tools will fail to
use the technology properly," says James Cox, CEO of Varna, Ill.-based VAR
Crown International Distributing. Among other factors driving the
speech-recognition market, there are now voice-related standards that make
application customization and development easier, the need to create more
electronic documents to comply with governmental regulations, such as HIPAA,
and statutes guaranteeing technology access to the disabled, such as the
U.S. Rehabilitation Act, Americans with Disabilities Act, or Workers'
Compensation Laws. Both Kaberline and Crown
International are Custom Speech USA Market
Partners. Congratulations to both for their contributions to the
VARBusiness article. J. McAdams, "The Computer Has Ears," VARBusiness
(May 29, 2006)
Custom Speech USA, Inc.
3 North Court Street, Suite B365
Crown Point, IN 46307
219-662-3800 (v)
219-662-3877 (f)
www.customspeechusa.com
info@customspeechusa.com
We teach computers how to listen®
Use
our Online Information Request Form
You are receiving
this copy of the Custom Speech USA, Inc. newsletter because you have
expressed interest in our products and
services. If you have been sent a newsletter in error, or would like
to be removed from the list, please click
here.
Price,
terms, specifications, and availability are subject to change without
notice. Custom Speech USA, Inc. trademarks are indicated. Other marks are
the property of their respective owners. Click here for
Online Privacy Policy.
Dragon
and NaturallySpeaking® are
licensed trademarks of Nuance® (Nuance
Communications, Inc.)
|
