| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 42-50 |
| Abstraksi Narasi | : | Providing the computer with a natural interface,including the ability to understand human speech, has been a research goal for almost 40 years. Practical versions of such systems have become moderately usable and commercially successful only in the past few years, however. To date, statistical modeling techniques trained from hundreds of hours of speech have provided most speech recognition advancements. Although it may appear that we have far to go to before these systems can match human performance, if researchers maintain the current rate of yearly progress in reducing word error rates, that objective should be within reach in less than a decade. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 38-41 |
| Abstraksi Narasi | : | - |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 92-94 |
| Abstraksi Narasi | : | - |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 58-66 |
| Abstraksi Narasi | : | Despite recent advances, multimedia use in knowledge management remains largely limited to retrieval systems. Multimedia data introduces several challenges to KM systems, including the uncertainties associated with media analyzers and the need for good scalability and effective user interfaces. Architectures capable of handling system complexity will also play a crucial role in deploying multimedia-based KM solutions. The prospects for fully exploiting multimedia content are promising. Given current trends in audio and video analysis, multimedia storage and distribution over the Internet, developments in XML representations, and integration with knowledge portals, the authors except multimedia data to become truly pervasive. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 17-19 |
| Abstraksi Narasi | : | - |
| Nama Pengarang | : | Allen L. Gorin dkk, Linda Dailey Paulson, Pedro J. Moreno dkk, Dharma P. Agrawal, Rashmi Bajaj, Samantha Lalinda Ranaweera, Savitha Srinivasan, Eric Brown, Mukund Padmanabhan, Michael Picheny, Gary McGraw, Bob Colwell, Nachiketh R. Potlapally, Holmes, Neville, Richard H. Thayer, Michael Macedonia, James Korris, Donald Welch, Daniel Ragsdale, Wayne Schepens |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 51-56 |
| Abstraksi Narasi | : | Traditional menu-driven speech recognition systems force users to learn the machine`s jargon, but many people can`t or won`t navigate such highly structured interactions. AT&T`s ``How May I Help You?`` technology shifts the burden to the machine by requiring it to adapt to human language and understand what people actually say rather than what a system designer expects them to say. For a given task, it is more crucial to recognize and understand some linguistic events than others. The authors have developed algorithms that automatically learn the salient words, phrases, and grammar fragments for a given task far more reliably than other methods. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 30-37 |
| Abstraksi Narasi | : | In criminal justice systems, incompatible content and information formats often create barriers to data acces and utilization that make knowledge management a complex and daunting process. To address these problems, the authors undertook the Coplink project, which bridges the gap between conducting technology research and helping police officers fight crime. University of Arizona researchers originally generated the concept space approach to facilitate semantic retrieval of information. Although Coplink`s current incarnation demonstrates its potential as a tool for enhancing the effectiveness of law enforcement, new technologies will provide opportunities for making the system even more useful. Meanwhile, several user studies have shown that this system also improves searching and browsing in the engineering and biomedicine domains. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 38-43 |
| Abstraksi Narasi | : | During the 2001 major league baseball season, the strike zone received special attention when officials decided to enforce the game`s original definition, which made tracking pitches especially important. Tracking the flight of a pitch during a live broadcast presents two major challenges, however:speed and image-processing reliability. Meeting these challenges required developing a complex system that fuses high-end computer graphics with a sophisticated algorithm for calculating flight trajectories. ESPN`s K Zone pitch-tracking system uses computer-generated graphics to create a shaded, translucent box that outlines the strike zone boundaries for viewers. Behind the flashy graphics, K Zone provides a sophisticated computing subsystem that monitors each pitch`s trajectory. Its development model may well prove effective in future computer vision projects, regardless of the application domain. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 66-71 |
| Abstraksi Narasi | : | Millions of individuals operating independently author the web`s information. Despite its decentralized nature, the authors` work shows that the Web self-organizes and its link structure allows efficient identification of communities. This is significant because no central authority or process governs hyperlink formation and structure. A Web community is a collection of Web pages in which each member page has more hyperlinks within the community than outside it. Compared to previous methods of finding related Web pages, the outhors describe an approach that retains the transparency of methods such as cocitation and biliographic coupling in explaining why pages belong to a community, yet can identify Web communities of arbitrary dimensions. Applications of their method include creating improved search engines, content filtering, and objective analysis of Web content and the relationship between Web Communities. |
| Nama Pengarang | : | - |
| Nama Majalah/Jurnal | : | - |
| Volume / Nomor Edisi | : | - |
| Nomor Halaman | : | 104-106 |
| Abstraksi Narasi | : | - |