Tight integration of neural- and clustering-based diarization through deep unfolding of infinite Gaussian mixture model.
Keisuke KinoshitaMarc DelcroixTomoharu IwataPublished in: CoRR (2022)
Keyphrases
- gaussian mixture model
- tight integration
- speaker identification
- mixture model
- feature vectors
- speaker recognition
- maximum likelihood
- em algorithm
- gaussian distribution
- feature space
- expectation maximization
- speaker diarization
- background subtraction
- gaussian model
- bayesian information criterion
- data mining
- feature transformation
- gaussian mixture
- gaussian mixture modeling