Data processing: speech signal processing – linguistics – language – Speech signal processing – Application
Reexamination Certificate
2001-11-30
2004-08-31
Dorvil, Richemond (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Application
C704S257000
Reexamination Certificate
active
06785654
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The invention relates to a distributed speech recognition system. More particularly, the invention relates to a distributed speech recognition system in which the speech recognition engines are provided with multiple functionalities from which an administrator may chose in optimizing the performance of the distributed speech recognition engine.
2. Description of the Prior Art
Recent developments in speech recognition and telecommunication technology have made automated transcription a reality. The ability to provide automated transcription is not only limited to speech recognition products utilized on a single PC. Large systems for automated transcription are currently available.
These distributed speech recognition systems allow subscribers to record speech files at a variety of locations, transmit the recorded speech files to a central processing facility where the speech files are transcribed and receive fully transcribed text files of the originally submitted speech files. As those skilled in the art will certainly appreciate, such a system requires substantial automation to ensure that all speech files are handled in an orderly and efficient manner.
Prior systems have relied upon a central processing facility linked to clusters of speech recognition engines governed by a speech recognition interface. In accordance with such systems, speech files enter the central processing facility and are simply distributed amongst the plurality of speech recognition clusters with no regard for the efficiency of the cluster to which the file is assigned or the ability of specific speech recognition engines to handle certain speech files. As such, many of the faster speech recognition engines linked to the central processing facility are oftentimes unused while other, slower, speech recognition engines back up with jobs to process.
These prior systems further include speech recognition engines which are permanently designated for the performance of specific functions. For example, speech recognition engines in accordance with prior art system are designated for the performance of either fluency analysis, speech recognition, adaptation, language model identification and word addition, regardless of the changing needs of the overall distributed speech recognition systems.
As those skilled in the art will certainly appreciate, static assignment of functionality as employed in prior distributed speech recognition systems is oftentimes not an effective way in which to use system resources. For example, upon the inception of a new distributed speech recognition system a great need exists for fluency analysis and adaptation as new users of the system will regularly start using the system. However, as the system becomes more established, more users are established and produce substantial speech files for recognition by the system while fewer new users are being added to the overall system. With the foregoing in mind, the specific resources required by a distributed speech recognition system is continually changing and statically defined functionalities limit the system's ability to perform in an optimal manner.
With the foregoing in mind, a need currently exists for a distributed transcription system capable of adapting as the required resources of the distributed speech recognition system change over time. The present system provides such a distributed speech recognition system.
SUMMARY OF THE INVENTION
It is, therefore, an object of the present invention to provide a distributed speech recognition system including a speech processor linked to a plurality of speech recognition engines. The speech processor includes an input for receiving speech files from a plurality of users and storage means for storing the received speech files until such a time that they are forwarded to a selected speech recognition engine for processing. Each of the speech recognition engines includes a plurality of servers selectively performing different functions. The system further includes means for selectively activating or deactivating the plurality of servers based upon usage of the distributed speech recognition system.
It is also an object of the present invention to provide a distributed speech recognition engine wherein the plurality of servers are selected from the group consisting of an acoustic adaptation logical server, a language model adaptation logical server, a speech recognition server, a language model identification server and a fluency server.
It is another object of the present invention to provide a distributed speech recognition engine wherein the means for activating or deactivating includes an administrator workstation.
It is a further object of the present invention to provide a distributed speech recognition engine including a speech engine monitoring agent monitoring usage of the plurality of speech recognition engines.
It is also an object of the present invention to provide a method for optimizing the operation of a distributed speech recognition system. The method is achieved by first linking a speech processor to a plurality of speech recognition engines, the speech processor including an input for receiving speech files from a plurality of users and storage means for storing the received speech files until such a time that they are forwarded to a selected speech recognition engine for processing. Each of the speech recognition engines is then provided with a plurality of servers performing different functions and the plurality of servers are selectively activated or deactivated based upon usage of the distributed speech recognition system.
Other objects and advantages of the present invention will become apparent from the following detailed description when viewed in conjunction with the accompanying drawings, which set forth certain embodiments of the invention.
REFERENCES:
patent: 5179627 (1993-01-01), Sweet et al.
patent: 5333275 (1994-07-01), Wheatley et al.
patent: 5513298 (1996-04-01), Stanford et al.
patent: 5649060 (1997-07-01), Ellozy et al.
patent: 5727950 (1998-03-01), Cook, deceased et al.
patent: 5772585 (1998-06-01), Lavin et al.
patent: 5787230 (1998-07-01), Lee
patent: 5799273 (1998-08-01), Mitchell et al.
patent: 5819220 (1998-10-01), Sarukkai et al.
patent: 5848390 (1998-12-01), Matsumoto
patent: 5884262 (1999-03-01), Wise et al.
patent: 5893134 (1999-04-01), O'Donoghue et al.
patent: 6058104 (2000-05-01), Snelling et al.
patent: 6064957 (2000-05-01), Brandow et al.
patent: 6076059 (2000-06-01), Glickman et al.
patent: 6081780 (2000-06-01), Lumelsky
patent: 6094635 (2000-07-01), Scholz et al.
patent: 6101467 (2000-08-01), Bartosik
patent: 6122613 (2000-09-01), Baker
patent: 6122614 (2000-09-01), Kahn et al.
patent: 6125284 (2000-09-01), Moore et al.
patent: 6195641 (2001-02-01), Loring et al.
patent: 6208964 (2001-03-01), Sabourin
patent: 6260011 (2001-07-01), Heckerman et al.
patent: 6263308 (2001-07-01), Heckerman et al.
patent: 6269188 (2001-07-01), Jamali
patent: 6282652 (2001-08-01), Scheifler
patent: 6298326 (2001-10-01), Feller
patent: 6308158 (2001-10-01), Kuhnen et al.
patent: 6338038 (2002-01-01), Hanson
patent: 6366882 (2002-04-01), Bijl et al.
patent: 2001/0020226 (2001-09-01), Minamino et al.
patent: 2001/0029452 (2001-10-01), Chen
patent: 2000172483 (2000-06-01), None
patent: 2002091477 (2002-03-01), None
patent: WO 00/54252 (2000-09-01), None
Elmasri, et al., “Fundamentals of database Systems”,The Benjamin Cummings Publishing Company, Inc.,pp. 76-79.
Hundt, et al., “Speech Processing in Radiology,Computer Applications”, European Radiology, Eur. Radiol.9, pp. 1451-1456 (1999).
F. Jelinek, “Self-Organized Language Modeling for Speech Recognition”,Language Processing for Speech Recognition, pp. 450-505.
Leggetter, et al., “Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models”,Computer Speech and Language(1995) 9, pp. 171-185.
Neumeyer et al., “A Comparative Study of Speaker Adaptation Techniques”,ESCA Eurospeech '95, 4thEuropean Confere
Cyr James
Greene Channell
Hold Martin
Kuhnen Regina
MacGintie Andrew
Azad Abul K.
Dictaphone Corporation
Dorvil Richemond
Howrey Simon Arnold & White , LLP
Meola Anthony L.
LandOfFree
Distributed speech recognition system with 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 Distributed speech recognition system with speech..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Distributed speech recognition system with speech... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3352292