Visual speaker identification and authentication by joint spatiotemporal sparse coding and hierarchical pooling.
Jun-Yao LaiShi-Lin WangAlan Wee-Chung LiewXing-Jian ShiPublished in: Inf. Sci. (2016)
Keyphrases
- sparse coding
- speaker identification
- sparse representation
- unsupervised learning
- natural images
- image classification
- spatial pyramid matching
- speech recognition
- gaussian mixture model
- linear combination
- generative model
- image representation
- speech signal
- feature extraction
- broadcast news
- visual features
- visual information
- feature space
- noisy environments
- high dimensional
- visual words
- data sets
- information retrieval
- mixture model
- face recognition
- high level
- multiscale
- denoising
- supervised learning
- image features
- low level