Data processing: speech signal processing – linguistics – language – Speech signal processing – Synthesis
Reexamination Certificate
1998-02-20
2001-04-10
Dorvil, Richemond (Department: 2741)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Synthesis
C704S270000
Reexamination Certificate
active
06216104
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates generally to a computer system for enabling access of records in electronic form via a network, such as an intranet, which includes a facility for delivery of messages. In its particular aspects, the present invention relates to such a system in which audible messages are generated by text-to-speech synthesis. The invention is particularly useful in the medical domain in conjunction with Computer-based Patient Record (CPR) systems and in the provision of alerts to physicians and other health care professionals.
2. Description of the Related Art
CPR systems maintain multimedia patient records of one or more health care institutions such as histories, reports, charts, and images in electronic digital form in a server system so that authorized users may access the records remotely employing user equipment, such as desktop or portable computing devices, coupled to the server system via wired and/or wireless network paths.
Speech interfaces for computer systems can employ speech recognition for command and control, thereby providing for hands-free navigation by the user. Also, useful information can be optimally arranged on screen and the user can remain focussed thereon by eliminating distracting and space consuming Graphical User Interface (GUI) control objects such as buttons, hot spots and/or menus that are typically used with a mouse or other pointing device. Speech recognition for dictation can enable health care personnel to enter reports when their hands are busy or where touching a keyboard would be a hygiene risk.
Text-to-speech synthesis can provide background notification of events and status changes, such as printer activity, by speech synthesized messages thereby avoiding visual distraction of the user. The use of synthesized speech for audible messages also minimizes storage requirements for the messages.
A Java® Speech Application Programming Interface (API) is substantially available to support speech synthesis, command-and-control recognizers and dictation systems. The Java® Speech API includes a Java® Speech Markup Language (JSML) for speech synthesis and a Java® Speech Grammar Format (JSGF) for speech recognizers. JSGF provides rule-based grammar indicating possible alternative commands, actions, objects, and their relative probabilities. JSML supports explicit specifications for delimited words and phrases such as structure (paragraph and sentence), special handling of dates and times, breaks, and prosodic information (speaking rate, volume, baseline pitch, pitch range).
In hospital environments, health care personnel are not always at their user equipment devices and there is a need to issue alerts and reminders via the CPR system which can be received via a variety of message delivery vehicles, such as voice mail, pager, and electronic mail. Further, there is a need that such alerts and reminders when delivered as audible messages have appropriate clarity, structure, and prosodic characteristics, so they are easily understandable and receive attention appropriate to the nature of the information conveyed.
SUMMARY OF THE INVENTION
It is an object of the present invention to provide a message delivery facility in a computer network system which includes speech synthesis of text specified in a speech markup language, such as JSML.
It is a further object of the present invention that the text specified in speech markup language include speaker profile information so that the message may be personalized with prosodic characteristics of the voice of a predetermined person, for example the originator of the message, in order to invoke appropriate attention by the recipient.
It is yet another object of the present invention that the computer system provide for delivery of messages in accordance with a message delivery profile of the recipient indicating which message delivery vehicles should be used and in what order.
Briefly, these and other objects are achieved by providing a computer system, including a server system and user equipment devices coupled thereto by a network, wherein the server system has access to a storage system containing user specific information including speech synthesis profiles of users of the system, each profile of a user including prosodic information for synthesizing vocal characteristics of the user, such as baseline pitch and pitch range, and including message delivery profiles of users indicating which of a plurality of possible message delivery vehicles are to be used, and in what order. The computer system has the capability of generating messages in the form of speech markup language text which includes prosodic information of a predetermined person associated with the message, usually the originator, to be initiated and supplied to a message delivery system for delivering the message to the recipient in accordance with the recipient's stored message delivery profile.
The message delivery system includes a speech synthesizer for receiving the speech markup language text and synthesizing therefrom an audible message, which is similar in vocal characteristics to the predetermined person, and also appears clear and natural due to the use of delimiters in the markup language text specifying emphasis or volume, speaking rate, and items to be said as dates and times. The message delivery system includes as one of the message delivery vehicles, a voice mail facility which receives synthesized speech from the speech synthesizer. Other message delivery vehicles of the message delivery system include a pager system, and an electronic mail system.
Other objects, features and advantages of the present invention will become apparent upon perusal of the following detailed description when taken in conjunction with the appended drawing, wherein:
REFERENCES:
patent: 5243643 (1993-09-01), Sattar et al.
patent: 5333266 (1994-07-01), Boaz et al.
patent: 5493692 (1996-02-01), Theimer et al.
patent: 5633910 (1997-05-01), Cohen
patent: 5706507 (1998-01-01), Schloss
patent: 5721827 (1998-02-01), Logan et al.
patent: 5732216 (1998-03-01), Logan et al.
patent: 5742668 (1998-04-01), Pepe et al.
patent: 5761201 (1998-06-01), Vaudreuil
patent: 5812865 (1998-09-01), Theimer et al.
patent: 5845255 (1998-12-01), Mayaud
patent: 5884266 (1999-03-01), Dvorak
patent: 2134132 (1995-07-01), None
patent: WO 99/42932 (1999-08-01), None
MIT Media Laboratory. Arons, “Hyperspeech: Navigating in a speech-only Hypermedia”., PP 133-146. Dec, 1991.*
Speech Communication. Taylor et al., “SSML: a speech synthesis markup language” vol. 21, p. 123-33, Feb. 1997.*
“SSML: A Speech Synthesis Markup Language”, by P. Taylor et al., Speech Communication 21, 1997, pp. 123-133.
Glicksman Robert A.
Moshfeghi Mehran
Dorvil Richemond
Philips Electronics North America Corporation
Vodopia John F.
LandOfFree
Computer-based patient record and message delivery system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Computer-based patient record and message delivery system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Computer-based patient record and message delivery system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2460948