Speaker normalization via a linear transformation on a perceptual feature space and its benefits in ASR adaptation.
Gu YongJohn S. MasonPublished in: EUROSPEECH (1989)
Keyphrases
- linear transformation
- feature space
- automatic speech recognition
- speech recognition
- kernel trick
- metric learning
- linear transformations
- linear model
- distance metric
- speech signal
- dimensionality reduction
- training set
- high dimensional
- hidden markov models
- supervised dimensionality reduction
- input space
- data points
- feature selection
- principal component analysis
- feature vectors
- kernel function
- support vector machine
- zernike moments
- kernel pca
- feature extraction
- image representation
- semi supervised
- lower dimensional
- high dimensional feature space
- image retrieval
- machine learning