Cycle-GANs for Domain Adaptation of Acoustic Features for Speaker Recognition.
Phani Sankar NidadavoluJesús VillalbaNajim DehakPublished in: ICASSP (2019)
Keyphrases
- high dimensional
- speaker recognition
- acoustic features
- speaker verification
- cross domain
- speech signal
- noisy environments
- sentiment classification
- speaker identification
- transfer learning
- audio visual
- emotion recognition
- speech recognition
- language identification
- training data
- multilayer perceptron
- automatic speech recognition
- data sets
- sentiment analysis
- generative model
- text classification
- semi supervised
- feature vectors
- video sequences
- multimedia
- image processing
- information retrieval
- neural network