Maximum-Likelihood Linear Transformation for Unsupervised Domain Adaptation in Speaker Verification.
Abhinav MisraJohn H. L. HansenPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2018)
Keyphrases
- linear transformation
- speaker verification
- maximum likelihood
- noisy environments
- audio visual
- em algorithm
- emotion recognition
- language identification
- zernike moments
- linear model
- multilayer perceptron
- distance metric
- gaussian mixture model
- noise reduction
- neural network
- speaker identification
- image reconstruction
- artificial neural networks