Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification.
Saurabh KatariaJesús VillalbaLaureano Moro-VelázquezNajim DehakPublished in: INTERSPEECH (2022)
Keyphrases
- speaker verification
- domain adaptation
- speaker recognition
- noisy environments
- prosodic features
- emotion recognition
- audio visual
- cross domain
- semi supervised
- labeled data
- semi supervised learning
- multiple sources
- sentiment classification
- speech recognition
- test data
- multilayer perceptron
- transfer learning
- target domain
- information retrieval
- unlabeled data
- high dimensional
- document classification
- collaborative filtering
- data sets