Domain Adaptation for Speaker Recognition in Singing and Spoken Voice.
Anurag ChowdhuryAustin CozzoArun RossPublished in: ICASSP (2022)
Keyphrases
- domain adaptation
- speaker recognition
- speech recognition
- speaker verification
- speaker identification
- gaussian mixture model
- speech signal
- vector quantization
- automatic speech recognition
- acoustic features
- broadcast news
- emotion recognition
- probabilistic neural network
- cross domain
- semi supervised
- labeled data
- sentiment classification
- multiple sources
- test data
- music information retrieval
- semi supervised learning
- audio visual
- noisy environments
- audio features
- hidden markov models
- training data
- data sets
- image compression
- neural network
- unlabeled data
- pairwise
- training set
- image segmentation