A novel method for estimating the number of speakers based on generalized eigenvalue-vector decomposition and adaptive wavelet transform by using K-means clustering.
Ali Dehghan FiroozabadiPablo IrarrazavalPablo AdasmeDavid Zabala-BlancoCesar A. Azurdia-MezaPublished in: Signal Image Video Process. (2020)
Keyphrases
- computational complexity
- significant improvement
- objective function
- cost function
- feature set
- small number
- detection method
- high precision
- computational cost
- preprocessing
- decision trees
- wavelet analysis
- wavelet transform
- decomposition algorithm
- support vector machine svm
- computationally efficient
- decomposition methods
- edge detection
- high accuracy
- data sets
- support vector machine
- experimental evaluation
- image segmentation
- neural network