An Unsupervised Speaker Clustering Technique based on SOM and I-vectors for Speech Recognition Systems.
Hany AhmedMohamed S. ElarabyAbdullah M. MoussaMostafa ElhosinySherif M. AbdouMohsen A. RashwanPublished in: WANLP@EACL (2017)
Keyphrases
- speaker clustering
- partially supervised
- speech recognition systems
- speech recognition
- feature transformation
- speaker identification
- feature vectors
- gaussian mixture model
- unsupervised learning
- self organizing maps
- discriminant analysis
- dimensionality reduction
- input data
- k means
- neural network
- speech recognizer
- input space
- linear classifiers
- vector space
- hidden markov models
- speech signal
- feature extraction
- semi supervised
- noisy environments
- scale invariant
- principal components
- supervised learning
- mixture model
- language model
- automatic speech recognition
- support vector machine
- feature set