Robust Speaker Identification by Fusing Classification Scores with a Neural Network.
Kevin WilkinghoffPaul M. BaggenstossAlessia Cornaggia-UrrigshardtFrank KurthPublished in: ITG Symposium on Speech Communication (2018)
Keyphrases
- speaker identification
- neural network
- probabilistic neural network
- pattern recognition
- noisy environments
- feature transformation
- feature extraction
- classification accuracy
- feature vectors
- machine learning
- feature selection
- speech recognition
- gaussian mixture model
- feature space
- image classification
- text classification
- support vector
- high dimensional
- model selection