A convex hull approach to sparse representations for exemplar-based speech recognition.
Tara N. SainathDavid NahamooDimitri KanevskyBhuvana RamabhadranParikshit M. ShahPublished in: ASRU (2011)
Keyphrases
- convex hull
- speech recognition
- sparse representation
- dictionary learning
- language model
- hidden markov models
- speech synthesis
- face recognition
- speech recognizer
- image classification
- image patches
- automatic speech recognition
- regularized least squares
- high dimensional data
- pattern recognition
- signal processing
- dimensionality reduction
- image representation
- speech signal
- speech recognition systems
- training samples
- speaker identification
- speaker independent
- data points
- neural network
- speaker adaptation
- linear combination
- learning algorithm