New approaches to audio-visual segmentation of TV news for automatic topic retrieval

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 3, Issue , 2001, Pages 1397-1400

  Iurgel, U ^a   Meermeier, R ^a   Eickeler, S ^a   Rigoll, G ^a  

^a UNIVERSITY OF DUISBURG ESSEN   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; IMAGE SEGMENTATION; INFORMATION RETRIEVAL SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS;

AUDIO-VISUAL SEGMENTATION; AUTOMATIC TOPIC RETRIEVAL; HIDDEN MARKOV MODELS;

ACOUSTIC SIGNAL PROCESSING;

EID: 0034846553     PISSN: 15206149     EISSN: None     Source Type: Journal    
DOI: 10.1109/ICASSP.2001.941190     Document Type: Article

References (5)

1. Estimating the dimension of a model
2. Content-based video indexing of tv broadcast news using hidden Markov models
3. Model selection criteria for acoustic segmentation
4. Improved speaker segmentation and segments clustering using the Bayesian information criterion
5. Alert homepage