 |
 |
 |
 |
 |
 |
 |
 |
|
|
|
|
|
|
|
|
|
FOR IMMEDIATE RELEASE UISPEECH IDENTIFIES NEW APPLICATIONS FOR
SAIL LABS MEDIA MINING SYSTEM Near
Real Time Transcription and Closed Captioning Solution
Highly Beneficial
To Broadcast Monitoring Industry April
2, 2003--Los Angeles, CA—UISpeech, a
division of Uptime Integrated Systems has identified new
applications for the innovative Sail Labs Media Mining
System that will be introduced at the 2003 National
Association Broadcasters (NAB) Conference. This
technological platform will allow users to automatically
index and archive live broadcasts in real time and
transcribe events in near real time. Additionally, the
system’s closed captioning solution enhances the
closed captioning process of organizations by enabling
them to significantly reduce the man-hours necessary to
manually monitor live events. Ken Stirbl, President of
Uptime Integrated Systems made the announcement today.
The Media Mining System was created by Sail Labs
Technology, and is being launched by UISpeech
within the United States. Demonstrations of the Media
Mining System will be presented by appointment at the
convention. “This
new technological platform will create a revolution in
the way we take control of and take advantage of the
spoken word,” said Stirbl. Manually indexing, archiving, and transcribing events is an extensive process. Determining how to annotate this data to facilitate information retrieval for subsequent searchers at a later date is integral to making the information more accessible. By automating these processes, the Media Mining System immediately converts the media streams it receives (audio, video, satellite, etc.) to a Meta Data file and XML output file for indexing and archiving in real time. Aided by the systems sophisticated speech recognition technology, which is based on a context-sensitive statistical model of natural language, the spoken words of an individual are analyzed and interpreted according to their context and position within a sentence. The added features of the speech recognition technology coupled with the files being transcribed with time codes allows for easier retrieval of specific sound bytes which assists in story creation for live field stories, promos, movie trailers and much more. This system essentially eliminates manual logging as field tapes or other video sources are automatically transcribed with designated time codes allowing a producer to create editorial sound bytes for their pieces instantly. The Media Mining System offers a closed captioning solution that augments the current closed captioning systems in place at companies. Near real time transcription of events is utilized to create closed captioning on the lower third of the television screen. This solution would be highly beneficial for offline captioning for postproduction houses, studios and any news organizations that have vast libraries of footage that was never closed-captioned, as users could effectively and easily modify this footage to incorporate these changes by employing the system’s speech recognition technologies to transcribe and time code the recorded media. For broadcasts with pre-scripted coverage, the Media Mining System could enhance the closed captioning process during the newscast by processing the newscaster’s live voice and determining whether there are any discrepancies in the script from what was typed into the computer and what was actually said. The live transcription process would ensure a higher accuracy level for closed captioning. The Media Mining System is also equipped with a keyword translation feature that enables the system to transcribe news from Arabic to English and from Spanish to English without the user needing any prior knowledge of these languages. The benefits of this solution significantly reduce the need for manual monitoring. Media
Mining System is equipped with a series of spoken
language technologies including speaker change
detection, speech recognition, speaker
identification, named entity detection
and topic detection. Media streams (audio, video,
satellite) pass through the Media Indexer and are
converted to a Meta Data file and XML output file for
archiving. All files are easily accessible through a
graphical user interface connected to the Media Mining
Server enabling the user to search, summarize and replay
audio/video content in real time. About UISpeech
UISpeech, a division of Uptime Integrated Systems, Inc
(UIS), is at the forefront of speech
communications technology for the broadcasting industry,
in addition to other diverse industry sectors.
UISpeech is able to customize and
integrate Sail Labs technology with other companies’
technologies to satisfy the unique requirements of each
client in Media Mining. Our primary
function is to integrate Media Mining and Speech
Recognition Technology into new or existing systems,
corporate networks and Oracle Data Centers. UISpeech
will create custom Interfaces and Enhanced support
function modules, which will get the most out of the
Media Mining Technology. For more information
visit www.uispeech.com. |