Maximum-Likelihood Online Speaker Diarization in Noisy Meetings Based on Categorical Mixture Model and Probabilistic Spatial Dictionary.
Nobutaka ItoTakashi MakinoShoko ArakiTomohiro NakataniPublished in: ICASSP (2018)
Keyphrases
- mixture model
- speaker diarization
- maximum likelihood
- bayesian information criterion
- em algorithm
- generative model
- gaussian mixture model
- probabilistic model
- expectation maximization
- generalized em algorithm
- speech recognition
- mixture modeling
- maximum a posteriori
- broadcast news
- speaker identification
- bayesian networks
- sparse representation
- gaussian distribution
- language model
- posterior probability
- unsupervised learning
- noisy environments
- high dimensional