Speech-based and video-supported indexing of multimedia broadcast news

ABSTRACT

This paper describes an automatic content indexing system for news programs, with a special emphasis on its segmentation process. The process can successfully segment an entire news program into topic-centered news stories; the primary tool is a linguistic topic segmentation algorithm. Experiments show that the resulting speech-based segments are fairly accurate, and scene change points supplied by an external video processor can be of help in improving segmentation effectiveness.

REFERENCES

• 1: Garofolo, J.S. et al. "The TREC Spoken Document Retrieval Track: A Success Story". Proc. of TREC-8, 1999.
• 2: Ohtsuki, K. et al. "Topic Extraction based on Continuous Speech Recognition in Broadcast News Speech", IEICE Trans. Vol.E85-D, No.7, pp.1138--1144, 2002.
• 3: Hayashi, Y. et al. "Searching Text-rich XML Documents with Relevance Ranking". Proc. of SIGIR2000 Workshop on XML and IR, 2000.
• 4: Marti A. Hearst, TextTiling: segmenting text into multi-paragraph subtopic passages, Computational Linguistics, v.23 n.1, p.33-64, March 1997
• 5: Bessho, K. "Text Segmentation Using Word Conceptual Vectors (in Japanese)". Trans. of IPSJ, Vol.42, No.11, pp.2650--2662, 2001.
• 6: Yukinobu Taniguchi , Akihito Akutsu , Yoshinobu Tonomura, PanoramaExcerpts: extracting and packing panoramas for video browsing, Proceedings of the fifth ACM international conference on Multimedia, p.427-436, November 09-13, 1997, Seattle, Washington, United States [doi>10.1145/266180.266396]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing

General Terms:
Algorithms, Design, Experimentation

Keywords:
automatic speech recognition, content indexing, metadata generation, topic segmentation