In Defence of Metric Learning for Speaker Recognition.
Joon Son ChungJaesung HuhSeongkyu MunMinjae LeeHee-Soo HeoSoyeon ChoeChiheon HamSunghwan JungBong-Jin LeeIcksang HanPublished in: INTERSPEECH (2020)
Keyphrases
- metric learning
- speaker recognition
- gaussian mixture model
- distance metric
- semi supervised
- vector quantization
- speaker verification
- pairwise
- speaker identification
- learning tasks
- dimensionality reduction
- distance function
- multi task
- feature space
- probabilistic neural network
- semi supervised learning
- speech signal
- feature vectors
- gaussian process regression
- speech recognition
- data sets
- mixture model
- support vector machine
- training set
- learning algorithm