论文信息 - Complementary Video AND Audio Analysis FOR Broadcast

Complementary Video AND Audio Analysis FOR Broadcast

1994, uniquely utilizes integrated speech and image and natural language understanding to process broadcast video. The project's goal is to allow search and retrieval in the video medium, similar to what is available today for text only. To enable this access to video, fast, high-accuracy automatic transcriptions of broadcast news stories are generated through

Alexander G. Hauptmann | Michael G. Christel | Andreas M. Olligschlaeger | Ricky A. Houghton

[1] S. Chiba,et al. Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[2] Takeo Kanade,et al. Human Face Detection in Visual Scenes , 1995, NIPS.

[3] Ralph Weischedel,et al. NAMED ENTITY EXTRACTION FROM SPEECH , 1998 .

[4] Alexander G. Hauptmann,et al. Learning to Recognize Speech by Watching Television , 1999, IEEE Intell. Syst..

[5] Ellen K. Hughes,et al. Video OCR for digital news archive , 1998, Proceedings 1998 IEEE International Workshop on Content-Based Access of Image and Video Database.

[6] Alexander G. Hauptmann,et al. Informedia: news-on-demand multimedia information acquisition and retrieval , 1997 .

[7] Stanley F. Chen,et al. Language and Pronunciation Modeling in the CMU 1996 Hub 4 Evaluation , 1999 .