Deep Speaker Embeddings with Convolutional Neural Network on Supervector for Text-Independent Speaker Recognition.
Danwei CaiZexin CaiMing LiPublished in: APSIPA (2018)
Keyphrases
- convolutional neural network
- face detection
- gaussian mixture model
- neural network
- speech recognition
- unsupervised learning
- deep learning
- detection method
- low dimensional
- computer vision
- dimensionality reduction
- object detection
- hidden markov models
- pattern recognition
- vector space
- manifold learning
- feature extraction