DVI FORMS ALLIANCE WITH PHILIPS FOR SPEECH RECOGNITION.

Digital Voice, Inc. (DVI) and Philips Speech Processing (NYSE: PHG) have joined together to provide an elegant integration of digital dictation and speech recognition.

Very few physicians today are comfortable with correcting speech misrecognitions, since this significantly decreases their dictation and report-creation productivity. The primary focus of this partnership of leading technologies is on providing a digital dictation system with a user-friendly "back-end" speech recognition solution. This allows to dramatically reduce the cost of transcription, as well as turnaround time. As a consequence, transcriptionists are able to dramatically increase the throughput of reports and minimize the occurrence of backlogged work.

DVI SpeechPower integrates Philips' SpeechMagic speech-recognition engine with the DVI VoicePower digital dictation system, thereby providing a seamless migration path to the clinical documentation process of the future.

Philips' SpeechMagic 4.0 engine, is the latest client server speech recognition software aimed at professional, network-based applications for the medical market. It is a comprehensive software development kit (SDK) used by software vendors and system integrators to create state-of-the-art, integrated end-user applications with speech recognition. It is unique in its software design, as it supports real distributed networks, where dictation, recognition, and correction can be done independently of the location, over a LAN, WAN, or the Internet. Since the speech recognition core software and all user data are stored centrally on a server, authors are not limited to a certain workstation to use speech recognition and can take advantage of a commonly shared vocabulary. However with the on-line option authors may additionally create documents real-time and edit directly their reports.

The strength of the SpeechPower solution is that it is based on current work habits and workflow, hence authors do not even need to know that SpeechPower is involved. They can dictate as they have always done, using as input device such as the telephone, specialized dictation station, microphone-equipped PC, wireless device, or portable digital voice recorder (such as DVI MobileMD on a Pocket PC). The voice files generated on PCs or digital recorders are uploaded, via network or Internet, to VoicePower.

Customers can select, in VoicePower, the departments or individual authors whose dictations should be run through the SpeechMagic speech recognition engine. Thanks to a specialized medical context (vocabulary and language model), recognition accuracy is anticipated to be initially in the 90+% range for most authors, and constantly improves with continued use. The voice file, demographic data, and recognized text are then all sent to the PC workstation of a medical editor, typically a medical transcriptionist. With the appropriate interfaces, the report header is populated with the demographics, and the editor then plays back the dictation with the aid of a footpedal attached to the PC. Philips patented EasyEdit technology, featuring synchronous playback and highlighting of the recognized text, allows comfortable and easy correction of misrecognitions. The finalized report is sent back to VoicePower for distribution, or can be deposited directly in the HIS, CPR, medical transcription system, or electronic signature system.

SpeechPower is available as an equipment purchase or as a fee-per-line service.

About DVI

DVI, headquartered in Joplin MO, is a supplier of Windows-based digital dictation systems. VoicePower's installed base includes 5 of the 7 "Best Hospitals in the U.S." (according to U.S. News & World Report), the "Best Children's Hospital," the "Best Cancer Hospital," and most of the major transcription service companies. DVI sells dictation systems for all applications worldwide, but has its major focus on the healthcare market. The company pioneered, within the dictation industry: open-architecture, Windows-based, client/server, and fault-tolerant systems.

About Philips Speech Processing

Philips Speech Processing, a business unit of Royal Philips Electronics, is a provider of speech recognition, natural dialogue and language understanding technologies, with more than 40 years experience in the development and marketing of speech products. Philips offers a broad portfolio of speech technology solutions to the telecommunications, IT, automotive and consumer electronics industries. As a developer and provider of speech technologies in multiple languages, Philips has the largest installed base of speech recognition and natural language understanding systems in Europe, and is a large and growing provider of speech technology in the Americas and other regions of the world. Installations include call center services automation, telephony applications, professional dictation solutions, voice controlled devices and Internet applications. Visit www.speech.philips.com for additional information.

About Philips

Royal Philips Electronics of the Netherlands is one of the world's biggest electronics companies and Europe's largest, with sales of $33.5 billion (EUR 31.5 billion) in 1999. It is a provider of color television sets, lighting, electric shavers, color picture tubes for televisions and monitors, and one-chip TV products. Its 226,900 employees in more than 60 countries are active in the areas of lighting, consumer electronics, domestic appliances, components, semiconductors, medical systems, and IT services (Origin). Philips is quoted on the New York (NYSE: PHG), London, Frankfurt, Amsterdam and other stock exchanges.

Philips can be found on the World Wide Web at www.news.philips.com.

For more information, call 888/999-2012 x117.