Audio-Visual Voice Activity Detection Using Diffusion Maps.
David DovRonen TalmonIsrael CohenPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2015)
Keyphrases
- audio visual
- diffusion maps
- voice activity detection
- multi modal
- manifold learning
- noisy environments
- nonlinear dimensionality reduction
- dimensionality reduction
- semi supervised
- visual information
- speech recognition
- visual data
- multimedia
- action classification
- low dimensional
- high dimensional
- high dimensional data
- nearest neighbor
- activity recognition
- gaussian mixture model
- neural network
- text mining
- probabilistic model
- spatio temporal
- information retrieval