Speech recognition for a digital video library
β Scribed by Witbrock, Michael J. ;Hauptmann, Alexander G.
- Publisher
- John Wiley and Sons
- Year
- 1998
- Tongue
- English
- Weight
- 244 KB
- Volume
- 49
- Category
- Article
- ISSN
- 0002-8231
No coin nor oath required. For personal study only.
β¦ Synopsis
The standard method for making the full content of audio relevant selections, and permit them to be reused effecand video material searchable is to annotate it with hutively.
man-generated meta-data that describes the content in
Through the integration of technologies from the fields a way that the search can understand, as is done in the of natural language understanding, image processing, creation of multimedia CD-ROMs. However, for the huge speech recognition, and video compression, the Inamounts of data that could usefully be included in digital video and audio libraries, the cost of producing this formedia digital video library system (Christel et al.,
π SIMILAR VOLUMES
This work focuses on the search of a sample object (car) in video sequences and images based on shape similarity. We form a new description for cars, using relational graphs in order to annotate the images where the object of interest (OOI) is present. Query by text can be performed afterward to ex
## Abstract The Open Video Digital Library (OVDL) provides digital video files to the education and research community and is distinguished by an innovative user interface that offers multiple kinds of visual surrogates to people searching for video content. The OVDL is used by several thousand peo
## Abstract The author describes some of the challenges, decisions, and processes that affected the design and development of the search user interface for Version 2 of the Digital Library for Earth System Education (DLESE; www.dlese.org), released July 29, 2003. The DLESE is a communityβled effort
Two experiments investigated the cognitive e$ciency of using speech recognition in combination with the mouse and keyboard for a range of word processing tasks. The "rst experiment examined the potential of this multimodal combination to increase performance by engaging concurrent multiple resources