Structuring Soccer Video Based on Audio Classification and Segmentation Using Hidden Markov Model.
Jianyun ChenYunhao LiSongyang LaoLing-Da WuLiang BaiPublished in: CIVR (2004)
Keyphrases
- hidden markov models
- estimate the model parameters
- visual speech
- speech recognition
- multi stream
- markov model
- conditional random fields
- image segmentation
- audio signals
- markov models
- sequential data
- discriminative training
- hidden state
- gesture recognition
- feature extraction
- pattern recognition
- feature selection
- image classification
- segmentation method
- handwritten word recognition
- feature space
- viterbi algorithm
- level set
- automatic speech recognition
- text classification
- unsupervised learning
- phoneme recognition
- continuous hidden markov models