Abstract
In this paper, we present an audio-based event detection approach shown to be effective when applied to sports broadcast data. The main benefit of this approach is the ability to recognise patterns that indicate high levels of crowd response which can be correlated to key events. By applying Hidden Markov Model-based classifiers, where the predefined content classes are parameterised using Mel-Frequency Cepstral Coefficients, we were able to eliminate the need for defining a heuristic set of rules to determine event detection, thus avoiding a two-class approach shown not to be suitable for this problem. Experimentation indicated that this is an effective method for classifying crowd response in football matches, thus providing a basis for automatic indexing and summarisation.
Original language | English |
---|---|
Journal | Lecture Notes in Computer Science |
Publication status | Published - 2003 |
Keywords
- information retrieval
- learning objects
- sport
- mel-frequency cepstral coefficients